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

pm-report

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's preamble contains shell commands that execute a local script check-update.sh and perform workspace initialization tasks such as directory creation (mkdir -p). These actions are standard for setting up a local reporting environment.
  • [PROMPT_INJECTION]: The skill facilitates the collection of untrusted data from users (e.g., performance metrics, feedback text) which is subsequently interpolated into generated reports. There is a risk of indirect prompt injection as the skill lacks explicit boundary markers or input validation, though this is a common characteristic of such reporting tools.
  • Ingestion points: Data collection occurs via AskUserQuestion in Steps 2 and 4.
  • Boundary markers: None present in the instructions.
  • Capability inventory: The skill has permissions for Write operations (to save reports) and the Bash tool.
  • Sanitization: No sanitization or escaping mechanisms for user input were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 06:20 AM
Security Audit — agent-trust-hub — pm-report