fact-check
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text from files or URLs provided via arguments. This data is ingested into the agent's context for analysis without specific boundary markers or sanitization, creating a surface where malicious instructions within the source text could attempt to influence agent behavior.\n
- Ingestion points: The skill accepts a file or URL as a primary argument ($ARGUMENTS) as defined in SKILL.md.\n
- Boundary markers: The prompt instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the input text.\n
- Capability inventory: The skill has permission to use tools including WebSearch, WebFetch, Read, Grep, Glob, and Task.\n
- Sanitization: There is no evidence of input validation or sanitization of the external content before processing.
Audit Metadata