octocode-research
Warn
Audited by Snyk on May 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill calls public code and package sources (e.g., githubSearchCode and githubGetFileContent, packageSearch via POST /tools/call/:toolName) and its Phase 4 "Research Loop" in SKILL.md requires the agent to read tool responses' "hints" and follow them to decide next tool calls and actions, so untrusted, user-generated third‑party content from GitHub/npm/PyPI can materially influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata