octocode-rfc-generator

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests that the user manually install the octocode-mcp package using npx to enable research capabilities. This introduces a dependency on an external, unverified package outside of the standard trusted vendor list.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core research workflow.\n
  • Ingestion points: The agent retrieves data from external repositories and package registries using tools such as githubSearchCode, githubGetFileContent, and packageSearch (SKILL.md).\n
  • Boundary markers: The instructions do not define strict delimiters or warnings to the agent to disregard instructions that may be embedded in the retrieved code or documentation.\n
  • Capability inventory: The agent has the ability to read local file contents (localGetFileContent) and save generated RFC documents to the .octocode/rfc/ directory.\n
  • Sanitization: There are no documented steps for validating or sanitizing the content retrieved from external research tracks before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 02:18 PM
Security Audit — agent-trust-hub — octocode-rfc-generator