afk-to-prd-spec

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run the command plannotator annotate --gate <path> to validate the generated PRD artifact. This is a local process intended for quality control within the development workflow.
  • [PROMPT_INJECTION]: The skill processes untrusted external data, such as PM PRDs and feature notes, which presents an indirect prompt injection surface.
  • Ingestion points: Existing PRDs, conversation context, and user-provided feature notes referenced in SKILL.md.
  • Boundary markers: No explicit delimiters are used to isolate untrusted input from the agent's instructions.
  • Capability inventory: The skill has the capability to write files to the documentation directory and execute the plannotator command.
  • Sanitization: No specific sanitization or filtering of the ingested content was identified.
  • [SAFE]: No evidence of malicious behavior such as data exfiltration, credential harvesting, or unauthorized network access was found. The operations described are consistent with standard project documentation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 09:37 PM
Security Audit — agent-trust-hub — afk-to-prd-spec