injective-docs-style
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes shell commands to install secondary skills from GitHub repositories (
bguiz/devrel-agent-skillsandInjectiveLabs/agent-skills). The latter is the official repository for the vendor. - [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface as it processes external documentation files which could potentially contain malicious prompts.
- Ingestion points: The skill activates on and reads the content of
*.md,*.mdx, and*.txtfiles. - Boundary markers: There are no explicit instructions or delimiters used to separate the documentation content from the agent's internal instructions.
- Capability inventory: The skill has the capability to read local files, search an external Injective Documentation MCP server, and write report files back to the local disk.
- Sanitization: No evidence of input sanitization or filtering was found in the provided instructions.
Audit Metadata