skills/konglong87/superpm/pm-tech/Gen Agent Trust Hub

pm-tech

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill's preamble section executes a local script (check-update.sh) to verify the skill version and set up the documentation directory.
  • [NO_CODE]: The check-update.sh script referenced in the preamble is not included in the provided file package for review.
  • [PROMPT_INJECTION]: The skill processes user-provided project documentation, which creates a potential surface for indirect prompt injection.
  • Ingestion points: PRD and prototype markdown files (SKILL.md).
  • Boundary markers: The skill does not use explicit delimiters or instructions to ignore embedded commands when reading these files.
  • Capability inventory: The skill utilizes the Bash, Write, and Agent tools, which could be targeted by successful injection.
  • Sanitization: No sanitization or validation of the ingested document content is performed prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 06:20 AM
Security Audit — agent-trust-hub — pm-tech