memory-sync
Verify, deduplicate, and compact an explicitly inventoried set of project Codex instructions against current source facts; honors narrowed scope and excludes persistent personal memory unless directly requested.
74%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.codex/skills/memory-sync/SKILL.mdW011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow reads local git history (branch, commit, range, or recent commits) and the agent selects the revision, so outsider text could reach it only if an outsider lands commits in the repo, which is a publish-without-forced-delivery path and therefore low.
- Repository
kochetkov-ma/claude-brewcode
- Revision
5da825f
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.