competitive-intelligence
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on untrusted external data gathered via the WebSearch tool. Malicious instructions on external websites could potentially override the agent's behavior.
- Ingestion points: WebSearch tool output (SKILL.md).
- Boundary markers: Absent; there are no instructions provided to separate user instructions from retrieved web content.
- Capability inventory: Bash, Write, Edit, and Task (sub-agent spawning) are listed in allowed-tools (SKILL.md).
- Sanitization: Absent; the skill does not implement any filtering or verification of content retrieved from the web.
Audit Metadata