affiliate-disclosure-compliance
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted content from third-party sources, creating a potential attack surface for indirect prompt injection.
- Ingestion points: The skill accepts untrusted artefacts such as caption text, video scripts, transcripts, and live URLs for analysis (SKILL.md, Review Workflow Step 3).
- Boundary markers: The instructions do not define explicit delimiters to isolate the untrusted content from the skill's logic, which could allow adversarial text within a caption to influence the agent's behavior.
- Capability inventory: The skill utilizes a web browsing tool to fetch live content and verify regulator guidance (SKILL.md, Review Workflow Step 5). It does not have capabilities for shell access or persistent file modification.
- Sanitization: No explicit sanitization or filtering of the processed content is documented in the skill instructions.
Audit Metadata