planning-with-files
Warn
Audited by Snyk on Jul 28, 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). This skill’s workflow includes reading/writing
notes.md(andtask_plan.md) as “working memory,” and the provided examples explicitly show usingWebSearchto gather sources and then writing those findings intonotes.md, which—if those sources are fetched from the public web—would be outsider-authored free text that the LLM later reads fromnotes.mdduring “Read notes.md”.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata