defuddle
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse content from external web pages into a Knowledge Base.
- Ingestion points: External web content retrieved via the
defuddle parse <url>command. - Boundary markers: The instructions do not define delimiters or "ignore instructions" headers to separate ingested content from the agent's internal logic.
- Capability inventory: The skill utilizes shell command execution to parse URLs and specifies a file system target (
Sources/Web/) for the output. - Sanitization: There is no evidence of sanitization or filtering applied to the ingested content, which could allow malicious instructions embedded in web pages to be processed by the agent.
Audit Metadata