Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill fetches untrusted data from an external source (Instagram media captions) through the Graph API. This content is brought into the agent's context, potentially influencing its subsequent behavior.
- Ingestion points: File
SKILL.mddefines commands to fetchcaptionfields from the/mediaand/<media-id>endpoints. - Boundary markers: Absent. The skill does not provide instructions to the agent to delimit or ignore instructions found within retrieved captions.
- Capability inventory: The skill allows for network operations (
curl) and local file writes (/tmp/request.json). - Sanitization: Absent. No evidence of content filtering or escaping for retrieved data.
- COMMAND_EXECUTION (SAFE): The skill utilizes
bash -cfor executingcurlcommands to interact with legitimate Facebook/Instagram endpoints. This is used for standard API integration and environment variable management.
Audit Metadata