source-gathering
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external research sources.
- Ingestion points: Fetches papers and web pages using
brave-search,apify, andsemantic-scholaras described inSKILL.md. - Boundary markers: No explicit delimiters or boundary markers are defined in the protocol to separate untrusted external content from agent instructions.
- Capability inventory: The skill invokes the
wiki-ingest-sourceSOP to write raw material to immutable source pages and update a search index. - Sanitization: The protocol does not specify any sanitization, filtering, or validation steps for the content retrieved from external sources.
Audit Metadata