ptlam
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs standard file system operations to manage project instructions. It resolves the project root, reads a bundled reference file, and writes to
AGENTS.mdandAGENTS.override.md. These actions are consistent with the stated purpose of initializing project preferences. - [SAFE]: The content in
references/PTLAM_AGENTS.mdprovides stylistic and structural guidelines for agent responses (e.g., "Human-First Work Contract"). It explicitly instructs agents to follow system, user, legal, and safety instructions with highest priority. - [SAFE]: No network exfiltration, hardcoded credentials, or obfuscation techniques were detected. The skill uses explicit markers (
PTLAM-INIT:MANAGED) to identify and manage its own generated content, which is a good practice for idempotency and preventing accidental overwrites of user data.
Audit Metadata