collab-outreach
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to check for and read
.agents/youtube-context.mdin the project root to inform its collaboration strategy. This process lacks security boundaries or sanitization for the ingested data. - Ingestion points:
.agents/youtube-context.md(referenced in SKILL.md). - Boundary markers: The skill does not provide delimiters or instructions to ignore potential commands embedded within the read context file.
- Capability inventory: The skill does not utilize tools for network access, file writing, or shell command execution, limiting the impact of any potential injection.
- Sanitization: No logic is provided to validate or filter the content retrieved from the context file before it is processed by the agent.
Audit Metadata