instagram-content
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge for user-supplied visual descriptions to be processed by an external AI API, which constitutes an indirect prompt injection attack surface.
- Ingestion points: User-provided text strings within the 'content' field of the message payloads in the SKILL.md examples.
- Boundary markers: The skill lacks explicit delimiters or specific prompt instructions to distinguish and ignore malicious commands embedded in the user's input.
- Capability inventory: The skill is configured with Bash(curl) and WebFetch tools to perform network operations to the eachlabs.run infrastructure.
- Sanitization: The provided templates and scripts do not include steps for sanitizing, escaping, or validating the input data before it is sent to the remote API.
Audit Metadata