hermes-atlas-ecosystem-map
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires downloading project source code from an external GitHub repository:
https://github.com/ksimback/hermes-ecosystem.git. - [INDIRECT_PROMPT_INJECTION]: The RAG chatbot retrieves information from
data/repos.json, a community-curated file. Malicious data in this file could potentially manipulate the chatbot's outputs. - Ingestion points:
data/repos.jsonand markdown files in theresearch/directory. - Boundary markers: The retrieval pipeline lacks explicit delimiters or instructions to prevent the agent from following commands embedded in retrieved chunks.
- Capability inventory: The skill uses network operations to interact with OpenRouter, Redis, and the GitHub API.
- Sanitization: No validation or filtering is described for the community-contributed data before it is indexed or retrieved.
- [COMMAND_EXECUTION]: The instructions involve running several local commands and scripts, such as
npm install,node scripts/build-chunks.js, andvercel dev, which execute code with the user's system privileges.
Audit Metadata