Index of every page on this site: llms.txt
All skills
Run it yourself

Threat-models a change that crosses a trust boundary, turns each abuse case into a failing test, triages a scanner or advisory finding, and writes a design review into the design doc. Use when adding or changing auth, login, sessions, cookies, passwords, tokens, JWT, permissions, roles, user input, file uploads, webhooks, a fetch of a user-supplied URL, secrets, API keys, CORS, CSRF, XSS, SQL injection, a vulnerability, a CVE, a dependency or npm audit finding, a threat model, personal data, PII, GDPR, or an LLM feature that handles untrusted text, or when the user asks whether something is secure. Not for reviewing a whole diff - use `review`; not for Go-specific APIs - use go; not for SQL or schema design - use database.

  • 6 files
  • 26.2 KB
  • Updated 3 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/avik-creator/agent-skills/security

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

referencesllm.md

≈327 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Model and LLM features

Read when the feature calls a model, or puts text from a user, a page, a file, or a tool into a prompt. Model output is untrusted input. The system prompt is not a boundary.

  • Parse model output as data, then check it against an allowlist, then encode it for where it goes. Why: the text can be a query, markup, a path, or a tool argument.
  • Do not send the output into a query string, a shell, an HTML sink, or a file path. A tool runs only if the code allows that tool for this caller, and the code checks the arguments again.
  • Keep secrets, other tenants' data, and personal data out of the prompt and the retrieved context. Why: anything in the context can come back in the answer or land in a log.
  • Confirm a destructive or irreversible tool action with the user before it runs. Why: the model can be talked into calling it.
  • Cap tokens, request rate, and how deep a tool may call another tool. Take the limits from the product's own requirements.
  • If retrieval is stored per tenant, a query for one tenant must not read another's documents. Check a document before it is indexed.

Abuse cases to test: a user message that says to ignore the instructions and dump the prompt; a fetched page that contains a tool call; a completion that is inserted into a page as HTML.

Source: SKILL.md on GitHub

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 third-party reports yet.

Signed by skilld at a0324a3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 days ago.

Activeupdated 3 weeks ago

README badge

README badge for avik-creator/agent-skills/security