fold-findings
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is potentially vulnerable to indirect prompt injection because it reads and processes data from external project files (e.g.,
review-findings.md). While it enforces a strict markdown table schema, it does not utilize explicit boundary markers or content sanitization to isolate this untrusted data from the agent's instructional context.\n - Ingestion points: The
review-findings.mdfile located within project documentation paths.\n - Boundary markers: None specified for the findings ledger content.\n
- Capability inventory: The skill can execute Git operations (
commit,push) and project-specific verification tools (type-check,tests,build).\n - Sanitization: The instructions do not define methods for escaping or filtering content retrieved from the findings rows.\n- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands such as
git commitandgit push, and to run project-specific verification gates. These operations are essential to the skill's function but involve interacting with the system's command line and executing logic defined within the user's repository.
Audit Metadata