pragman-unfck
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The runtime workflow in SKILL.md ingests only user-selected session evidence (e.g., transcripts/JSONL/markdown) and treats transcript/tool output as untrusted evidence, but it does not perform any automatic browsing/search/URL fetching or read outsider-posted free text from external public feeds unless the user explicitly supplies excerpts after selecting sources/adapters.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata