strand-fact-check-cite
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from external websites to verify factual claims. This ingestion of untrusted data creates a surface for indirect prompt injection attacks, where malicious instructions embedded in web content could influence the agent's behavior.
- Ingestion points: The skill ingests user article text and external content retrieved from URLs via web search/fetch tools as described in the process steps.
- Boundary markers: The instructions lack specific delimiters or explicit 'ignore' directives to isolate the task instructions from the fetched external content.
- Capability inventory: The agent is directed to use network fetching tools and modify draft content, including writing to frontmatter blocks.
- Sanitization: No mention of sanitizing, escaping, or validating the content retrieved from the web before it is interpolated into the post or frontmatter metadata.
Audit Metadata