apex-status
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from local sources (git logs and project documentation) to generate summaries. This creates a standard surface for indirect prompt injection where malicious instructions could be embedded in commit messages or project files.
- Ingestion points: Processes output from
git log,git status, and various project files (README, CHANGELOG, TODO, etc.) as seen in the execution steps inSKILL.md. - Boundary markers: No explicit delimiters or instructions are used to separate untrusted content from the system instructions.
- Capability inventory: The skill is configured with access to
Bash,Write,Edit,WebFetch, andWebSearchtools in theSKILL.mdfrontmatter. - Sanitization: The instructions do not specify any validation or sanitization for the data read from the codebase before synthesis.
Audit Metadata