app-store-review
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted application source code. This represents an ingestion point for potential indirect prompt injection attacks. However, the skill provides specific instructions to the agent to avoid including user-sensitive data in its output and to follow a structured review process, which mitigates the risk.\n- [COMMAND_EXECUTION]: The skill describes a feedback process where the agent can report issues to the maintainer via the GitHub CLI (
gh). This capability is designed as a safe, human-in-the-loop workflow: it requires the agent to obtain explicit user consent, display the full draft for review before sending, and strictly forbids the inclusion of user code, credentials, or proprietary details.
Audit Metadata