monthly-report-generator
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. It delegates data gathering to sub-agents that ingest untrusted content from Git commit messages and GitHub Pull Request descriptions. Ingestion points: Commit logs and PR bodies retrieved via
gh pr list(Workflow Step 1). Boundary markers: Absent; there are no instructions to the sub-agents to ignore or delimit embedded instructions within the ingested data. Capability inventory: The skill has the ability to generate HTML files and performgit pushoperations to update project wikis (Workflow Step 5). Sanitization: None; the skill interpolates external descriptions directly into the report compilation process. - [COMMAND_EXECUTION]: The skill utilizes local shell commands, specifically
gitand the GitHub CLI (gh), to extract repository metadata, diffs, and history.
Audit Metadata