rea
Warn
Audited by Snyk on Nov 21, 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 required workflow runs rea's string and procedure extraction on a user-selected local binary or package, so any outsider-authored text (for example, strings from a third-party app) is ingested only after the agent chooses that specific target.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The only state-changing operation the skill establishes is writing task facts to a knowledge graph on the rea server, which is ordinary analysis-artifact recording rather than administration, but under the recall-first override it is ambiguous enough to score as a low operational change.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata