market-intel-brief
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and summarizes external content from web searches regarding industry news and funding rounds.
- Ingestion points: The skill searches for and curates external AI/ML news, funding data, and competitive moves (SKILL.md, Step 2).
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to help it distinguish between legitimate news content and potential malicious instructions embedded within that content.
- Capability inventory: The skill has the ability to write files (SKILL.md, Step 4) and potentially use network tools for email or Feishu integration.
- Sanitization: While there are guardrails against fabrication, there is no mention of filtering or sanitizing the raw external text before it is processed.
Audit Metadata