fact-check
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a utility designed to improve the reliability of agent responses by enforcing a structured verification process.
- [COMMAND_EXECUTION]: Step 3 of the procedure directs the agent to verify empirical claims by running commands or reading files. This functionality leverages the agent's existing toolset for verification purposes and is tied to the primary goal of factual accuracy.
- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection because it ingests and processes data from previous conversation turns to identify claims for verification.
- Ingestion points: Data is ingested from either the skill argument or the last 'CLANKER' response as specified in SKILL.md.
- Boundary markers: The skill requires the agent to quote the claim exactly, which provides a weak boundary for the ingested content.
- Capability inventory: The skill utilizes file system access, command execution, and network-enabled search tools to perform verification (SKILL.md).
- Sanitization: The skill does not explicitly describe any sanitization or validation of the claims before they are processed by tools.
Audit Metadata