perform-preflight
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains purely instructional markdown content providing a checklist for the AI agent to follow. It does not include executable scripts, shell commands, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow commands defined in a local project file (
CLAUDE.md). This creates a vulnerability surface where the agent might execute commands or follow instructions provided by that file, which could be modified by external contributors in a shared repository. - Ingestion points: Local project configuration file (
CLAUDE.md). - Boundary markers: Absent; the agent is directed to use commands directly from the file.
- Capability inventory: The agent is expected to run test runners, linters, and formatters based on the file content.
- Sanitization: None; the skill assumes the integrity of the local project files.
Audit Metadata