fact-checking
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content (articles, paragraphs, and statements) for analysis.
- Ingestion points: User-provided statements or full articles passed to the agent for fact-checking, as described in the workflow and usage sections of SKILL.md.
- Boundary markers: Absent. The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent to use when processing external text.
- Capability inventory: Analysis is restricted to prompt-based reasoning. No scripts, network calls (beyond informational source referencing), file-system writes, or subprocess executions are defined in the skill.
- Sanitization: Absent. The skill relies on the agent's internal safety filters when processing potentially malicious instructions hidden in the text to be fact-checked.
Audit Metadata