Index of every page on this site: llms.txt
All skills
openai avatar

/finding-discovery

@ec0d6c1
by openaiopenai/codex-security14k stars
1,108
Run it yourself

Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover candidate security findings in a repository or code change. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

Use this Skill: https://skilld.dev/gh/openai/codex-security/finding-discovery

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈71 tokens for metadata: the name and description. ≈1.2k when used: this file. ≈55 more on demand in 1 file.

Description uses 3.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈286 characters, or 3.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Security Finding Discovery

Identify technically plausible security vulnerabilities in the authorized source, using the threat model and applicable security policy. Discovery preserves evidence for later validation; it does not decide final severity.

Read ../../references/artifact-storage.md before saving output and ../../references/security-guidance.md before source review. Resolve applicable policy for each reviewed path, including delegated assignments. Honor explicit input and output paths; ask for an explicitly required input only when its absence prevents the requested analysis.

Select the Workflow

Standard and Deep workers use their coordinator's self-contained prompts rather than this phase skill.

  • Running compact diff: read the supplied inventory through list_codex_security_review_items, review every assigned changed file, and record all candidates once with record_codex_security_discovery_candidates. Do not create ranked worklists, per-finding ledgers, receipts, or discovery reports.
  • Standalone diff without a compact inventory: use ../security-scan/references/scan-artifacts-and-ledger.md for the changed-file worklist and retained phase artifacts.
  • Standalone repository discovery: apply the evidence criteria below to the authorized source and return the candidates and coverage limitations. Do not start a scan or run the diff worklist pipeline.

For a diff, inspect the actual changed behavior, including deleted files at the baseline revision. Follow supporting code far enough to understand the affected boundary; expand to sibling callers when a changed shared control affects them. Do not broaden into an unrelated repository audit.

Evidence Criteria

  • Trace attacker-controlled input or a privileged operation through the closest relevant control to the sink and security impact. Explain why the control is absent, bypassable, or applied to the wrong value or boundary.
  • Check runtime reachability and deployment assumptions. Record effective guards and containment as counterevidence; a safe sibling implementation does not establish that the candidate path is safe.
  • Preserve the root-control location as well as entrypoints, wrappers, concrete implementations, and sinks needed to understand the claim. When the claim covers several implementations, inspect those implementations rather than asserting that all are affected.
  • Keep independently reachable vulnerable instances addressable. Merge duplicate observations of the same source/control/sink/impact instead of splitting cosmetic variants; retain all affected locations and original candidate IDs when merging.
  • Follow explicit user or advisory seeds to their exact source and control. Record the evidence that supports, disproves, or leaves the seed unresolved; a nearby issue in the same family does not close it. Use only authorized source material and do not fetch advisory links without permission.
  • Distinguish concrete security impact from maintainability or robustness concerns. A crash, dangerous API, optional feature, or missing check is a lead, not a finding by itself. Carry plausible candidates with explicit proof gaps to validation rather than inventing evidence or discarding them for lack of a runnable reproduction.

Divide independent review assignments among available workers when useful, with the target, scope, relevant policy/model, and required result fields. The parent reviews unassigned work and reconciles duplicates. Do not repeat validation or attack-path phases inside discovery.

Candidate Output

For each candidate, retain:

  • Stable candidate ID and title; preserve supplied seed or ledger IDs and advisory references.
  • Affected file/line locations, labeling entrypoint/wrapper, root_control, sink, and concrete_implementation where useful.
  • Attacker-controlled source, closest control, sink or broken control, plausible impact, and the source evidence connecting them.
  • Counterevidence, deployment preconditions, unresolved questions, and what validation needs to establish.
  • CWE IDs when known, otherwise an empty list.
  • For repository or scoped-path instances, an instance key <family>:<file>:<line> when required by the caller.
  • For diff findings, relevant_lines only where relevant buggy behavior overlaps the diff.

Use the caller's structured candidate contract. For a legacy diff, save the discovery report and discovery receipts at the paths in ../../references/scan-artifacts.md; subsequent phases own their own evidence and receipts. Finish when assigned source review and concrete follow-ups are accounted for, recording unfinished review honestly. If no plausible candidates remain, return that result with the actual reviewed scope and limitations.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts27d3 checks · Risk SAFE
  • Gen Agent Trust Hub27d

    This skill includes security considerations such as command execution and a surface for indirect prompt injection. While these warrant review, they are used within the skill's intended functionality for discovering security vulnerabilities in code. See detailed analysis for context.

  • Socket27d

    No alerts

  • Snyk27d

    Risk: LOW · No issues

Signed by skilld at ec0d6c1. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last month

README badge

README badge for openai/codex-security/finding-discovery