skills/alemtuzlak/skills/to-prd/Gen Agent Trust Hub

to-prd

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local binary to display the generated documentation to the user.
  • Evidence: SKILL.md contains a PowerShell command Start-Process -FilePath "$env:LOCALAPPDATA\plannotator\plannotator.exe" -ArgumentList @('annotate', '<absolute-path>') to open the draft.
  • Note: This is a functional component of the skill intended to facilitate document review.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes data from external sources like GitHub PRs and Linear tickets.
  • Ingestion points: Phase 1 in SKILL.md resolves inputs from pull requests, tickets, and session history.
  • Boundary markers: No explicit boundary markers or delimiters are defined to isolate untrusted external content from the agent's instructions.
  • Capability inventory: The skill can write markdown files to the local repository and execute a local annotation tool.
  • Sanitization: No evidence of sanitization or validation of external content is documented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 10:49 AM
Security Audit — agent-trust-hub — to-prd