paid-social-creative-brief
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, specifically creator post captions and visual descriptions, which could contain hidden instructions intended to override the agent's behavior.
- Ingestion points:
SKILL.md(Information Gathering section, item 1: "The creator post"). - Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions embedded within the provided post content.
- Capability inventory: The skill is focused on text analysis and brief generation. No dangerous capabilities such as subprocess execution, network operations, or sensitive file writes were identified.
- Sanitization: No evidence of input sanitization or validation protocols for the ingested content.
Audit Metadata