authz-bypass
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 sends curl and Burp requests to a user-supplied TARGET application and reads its responses, which may contain other users' profile or content fields that are outsider-authored, so under recall-first scoring this is treated as low exposure rather than none.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill gives working commands that change remote application state, such as a privileged
deleteEventPOST and achangepasswordrequest against another user, which passes the operational-change gate at low. It fails the irreversible-operational-loss gate because the evidence shows only content/data deletion and account changes, with no explicit unrecoverable loss of operational function or state.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata