Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill integrates with the Instagram Graph API to fetch content such as media captions, which are controlled by external users and could contain instructions designed to influence the agent's behavior.
- Ingestion points: Untrusted data enters the agent context through the Instagram Graph API media endpoints (e.g.,
media?fields=id,caption...) as described inSKILL.md. - Boundary markers: The instructions do not define boundary markers or provide guidance to the agent to treat fetched API data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill enables network operations via
curland shell command execution viabash -cinSKILL.md, providing a potential path for exploitation if the agent obeys instructions found in fetched data. - Sanitization: There is no mention of sanitization, filtering, or validation for the content retrieved from the API before it is processed by the agent.
Audit Metadata