pir
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes conversation history, which is inherently untrusted data, and synthesizes it into permanent documentation in the
docs/pir/directory. If the conversation contains malicious instructions, they may be persisted and potentially affect future sessions that use these reports for context. - Ingestion points: Extracts incident details, root causes, and resolutions from the current conversation history in Phase 0.
- Boundary markers: No specific delimiters or safety warnings are used when interpolating chat history into the final markdown template.
- Capability inventory: The skill can execute shell commands (
mkdir,date) and write markdown files to the local filesystem, including appending toCLAUDE.md. - Sanitization: There is no explicit sanitization, filtering, or validation of the summarized content before it is written to disk.- [COMMAND_EXECUTION]: The skill uses standard shell commands to manage its operations. It executes
date +%Y-%m-%dto generate filenames andmkdir -p docs/pirto ensure the storage directory exists.
Audit Metadata