competitive-intel
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill outlines a process for ingesting data from external sources like social media and community platforms, creating a surface for potential indirect prompt injection.
- Ingestion points: The 'Collect' phase mentions analyst notes, communities, and social media.
- Boundary markers: The skill does not specify delimiters to separate external data from the agent's instructions.
- Capability inventory: No scripts or tool configurations are included in this skill file.
- Sanitization: The framework does not define validation or sanitization processes for ingested content.
- [NO_CODE]: The skill consists exclusively of markdown documentation and contains no executable logic, dependencies, or configuration settings.
Audit Metadata