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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 21, 2026, 10:04 AM
Issues
2