alterlab-nmc-community-manager
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface where untrusted data could influence agent actions or file outputs.\n
- Ingestion points: Untrusted data enters the agent's context through web search results and the reading of project files as specified in the workflow section of SKILL.md.\n
- Boundary markers: Absent. The instructions do not define delimiters or provide specific warnings to ignore instructions that might be embedded in the retrieved web content or project files.\n
- Capability inventory: The skill has the ability to perform web searches and write multiple types of markdown files (e.g., playbooks, moderation policies, calendars) directly to the project directory, as outlined in SKILL.md.\n
- Sanitization: Absent. No logic is provided to sanitize, validate, or filter content retrieved from external sources before it is used to generate deliverables.
Audit Metadata