ptlam-setup
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from existing project files, creating a potential surface for indirect instructions.
- Ingestion points:
AGENTS.mdand.gitignorewithin the user-specified project root. - Boundary markers: The skill uses defined markers (
<!-- PTLAM-SETUP-SKILL:START -->) to scope its modifications. - Capability inventory: Performs file read and write operations on
AGENTS.md,AGENTS.override.md, and.gitignore. - Sanitization: It uses marker-based replacement logic to isolate its changes from existing project content.
- [COMMAND_EXECUTION]: The skill requires the agent to inspect the project's working tree and version control status, necessitating the use of filesystem and Git commands.
Audit Metadata