fact-check
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources to verify claims, creating a surface for indirect prompt injection.
- Ingestion points: Content is retrieved from external URLs and third-party sources via
WebFetch,WebSearch,mcp__exa, and theghAPI as defined in the verification evidence rules. - Boundary markers: The instructions lack explicit delimiters or specific warnings to the verification agents to ignore instructions embedded within the fetched content.
- Capability inventory: The skill has the ability to execute
git commit,ghAPI commands, andnpxtool execution across its scripts. - Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is processed by the verification agents.
- [COMMAND_EXECUTION]: The skill instructions allow for the execution of
npx <tool> --helpto verify claims about software behavior. This pattern involves running CLI commands for tools that may be suggested by untrusted input. - [DYNAMIC_EXECUTION]: The use of
npxfacilitates the dynamic fetching and execution of external packages at runtime based on the subject of the fact-check.
Audit Metadata