keenable-deep-research
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are free of malicious patterns, obfuscation, or unauthorized commands. The decomposition and planning steps provide transparency and auditability for the agent's actions.
- [SAFE]: The skill implements secure credential handling by advising users to set
KEENABLE_API_KEYin environment variables rather than providing it in the chat. - [PROMPT_INJECTION]: The skill possesses an inherent surface for indirect prompt injection as it ingests untrusted data from external websites using tools like
fetch_page_content. This is a known risk for research-oriented skills, mitigated here by workflow requirements for cross-referencing and synthesis. - Ingestion points: External content fetched via
fetch_page_content(SKILL.md). - Boundary markers: Absent.
- Capability inventory:
search_web_pagesandfetch_page_content. - Sanitization: Absent.
Audit Metadata