security-pass
Skill0 starsChanged 5 days agoMITView on GitHub
Version: 0.1.0 Applies to: Coding agents Trigger: Load when the change touches authentication, authorization, user input, file handling, database queries, secrets, or external requests.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- rpraharaj/ai-sdlctheir own version, first seen Nov 1, 2026
- rpraharaj/ai-engineertheir own version, first seen Nov 1, 2026
- quocld/hephaestus-agent-skillstheir own version, first seen Oct 20, 2026
- raccioly/websec-validatortheir own version, first seen Oct 10, 2026
- bt2go/claude-skillstheir own version, first seen Aug 1, 2026
- ficaviolaodorata520/met-museum-mcp-servertheir own version, first seen Jun 1, 2026
Used with
Projects with it also use refactor-safely and write-tests.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
srclightSkillrefactor-safely
This skill should be used when the user asks to "refactor", "rename", "move", "change a function signature", "extract a method", "delete unused code", "clean up", or any modification that could break callers or dependents. Provides a pre-change safety checklist using srclight's graph tools to assess blast radius before touching code.
Also in 3 projects that use this
SentrySkillwrite-tests
Write tests following project conventions. Use when adding new tests or modifying existing ones.
Also in 3 projects that use this
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- quocld/hephaestus-agent-skills★ 8same name
- raccioly/websec-validator★ 2same name
- rpraharaj/ai-engineer★ 1same name
- bt2go/claude-skills★ 0same name
- ficaviolaodorata520/met-museum-mcp-server★ 0same name
- rpraharaj/ai-sdlc★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- code-review-hawkSkill
- research-first-devSkill
- templatesSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Check each item below against the change:
- Distinctive: line 25
Do not list items that do not apply just to look thorough.
- Distinctive: line 26
Do not give generic advice like "validate input" without naming the field and the rule.
- Distinctive: line 27
Do not mark Pass without checking the code.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Security Pass
Version: 0.1.0 Applies to: Coding agents Trigger: Load when the change touches authentication, authorization, user input, file handling, database queries, secrets, or external requests.
Goal
Catch the common security failure classes before the change ships, with a short, concrete checklist rather than a generic warning.
Instructions
- Identify the trust boundary the change crosses: user input, network, file system, database, third-party API.
- Check each item below against the change:
- Injection: SQL, command, template, header.
- Auth: is the action authorized for this user, not just authenticated?
- Secrets: any key, token, or password in code, logs, or errors?
- Input validation: length, type, encoding, allowlist.
- Output encoding: HTML, JSON, URL.
- File handling: path traversal, upload type, size limits.
- Dependencies: new package, pinned version, known vulnerability.
- Report only items that apply. Mark each as Pass, Fail, or Not Applicable.
- For each Fail, give the concrete fix.
Constraints
- Do not list items that do not apply just to look thorough.
- Do not give generic advice like "validate input" without naming the field and the rule.
- Do not mark Pass without checking the code.
Expected Output
A short table: Check, Status (Pass/Fail/Not Applicable), Note. Followed by a Fixes section for every Fail.
Example
Input: A change that adds a file download endpoint with a user-supplied filename. Behavior: The agent flags file handling Fail (path traversal) and gives the fix: resolve the path and reject anything outside the allowed directory. Output: One Fail with a concrete fix, all other checks marked Pass or Not Applicable.
Notes
This skill does not replace a full security audit. It catches the common classes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.