Social Media Strategist
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core function involves social listening and competitive intelligence, which requires reading and processing data from external, untrusted web sources.
- Ingestion points: External data enters the agent's context through tools used for web searching and fetching as part of its research workflow.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its core logic and potentially malicious instructions embedded in the external content it retrieves.
- Capability inventory: The agent has the ability to write and edit files, which could be exploited if the agent were to follow instructions hidden in the fetched data.
- Sanitization: The skill does not define any mechanisms for sanitizing or validating the content retrieved from social platforms before analysis or reporting.
Audit Metadata