agents-introspection
Warn
Audited by Snyk on Jul 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow reads Codex/Claude Code transcript JSONL files from local directories (e.g.,
~/.codex/sessions/...and~/.claude/projects/...) and extracts strings from them; these transcripts are not authored by the operating user and can contain outsider free text, which is then fed into the agent’s LLM context via the skill’s generated analysis/report.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata