instagram-content-generation

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill documentation describes an interface that accepts user-supplied text for content generation, creating a potential surface for indirect prompt injection.
  • Ingestion points: User input is accepted via the message field in JSON payloads for the /chat endpoint.
  • Boundary markers: No boundary markers or 'ignore' instructions are present in the provided examples.
  • Capability inventory: The skill facilitates network communication with the each::sense API via curl commands.
  • Sanitization: No evidence of sanitization or validation of the input content is provided in the documentation.
  • [NO_CODE]: This skill consists solely of Markdown documentation (SKILL.md and SSE-EVENTS.md) and does not include any executable scripts, binaries, or platform-specific configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:30 PM