career
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The file references/staff-engineer-progress.md provides shell commands including git log, find, and jq for the agent to execute. These commands are used to analyze technical writing density and system ownership within a local repository.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the GitHub CLI (gh) to retrieve pull request and review metadata from GitHub. This data is used to calculate code review activity and cross-team impact metrics.
- [PROMPT_INJECTION]: The skill processes untrusted data from repository commit messages and pull request metadata, representing an indirect prompt injection surface. Ingestion points: Output from git log and gh search prs commands. Boundary markers: No delimiters or instructions are present to ensure the agent ignores embedded instructions within the ingested text. Capability inventory: File system discovery via find and repository history access via git. Sanitization: There is no evidence of sanitization or content filtering for the ingested repository data.
Audit Metadata