social
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data as part of its 'listening' and 'reverse engineering' workflows, which could expose the agent to malicious instructions embedded in social media content.
- Ingestion points: The skill monitors public accounts, topics, and competitor terms, and analyzes public work for structure and pacing.
- Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from obeying instructions found within the analyzed social media content.
- Capability inventory: While the skill files themselves are markdown instructions and do not contain executable scripts, the agent using this skill typically possesses capabilities to generate content and browse the web.
- Sanitization: There are no instructions for sanitizing or escaping the content retrieved during the listening or reverse engineering processes.
Audit Metadata