doc-iplan-audit
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided IPLAN files as part of its auditing workflow.
- Ingestion points: It reads IPLAN documents from local project paths and playbooks from the framework root.
- Boundary markers: Instructions explicitly define artifact content as untrusted context and direct the agent to disregard any self-assessment scores found within the files.
- Capability inventory: The skill uses shell commands for file management and timestamping, writes audit reports to local directories, and spawns specialized subagents.
- Sanitization: It employs de-anchoring logic to ensure that the AI's quality assessment remains independent of any claims made by the document author.
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands for benign administrative tasks such as directory initialization and audit trail logging.
Audit Metadata