competitors
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it requires the agent to gather and analyze content from external, untrusted sources which could contain malicious instructions. \n
- Ingestion points: As specified in the 'Research Process' section of
SKILL.md, data is collected from competitor product sign-ups and third-party review platforms like G2, Capterra, and TrustRadius. \n - Boundary markers: There are no defined delimiters or 'ignore' instructions provided to the agent to separate the ingested external data from its primary instructions. \n
- Capability inventory: The skill's primary function is generating markdown text; it lacks high-risk capabilities such as arbitrary command execution, sensitive file system access, or network exfiltration functions. \n
- Sanitization: The instructions do not specify any mechanisms for validating, filtering, or sanitizing the content retrieved from external sources before processing.
Audit Metadata