tamper-fuzzing
Fail
Audited by Snyk on Jun 7, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). The document is an offensive tamper-fuzzing playbook that explicitly describes and provides runnable probes for SSRF/XXE OOB callbacks, blind/time-based injections, auth-token swapping, IDOR/BOLA sweeps, file upload write/exec, prompt-injection-to-tool calls, and other techniques enabling data exfiltration, remote code execution, and credential abuse — capabilities that are powerful and easily abused despite some stated safety gates.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow ingests outsider-authored free text from the target’s HTTP responses (e.g., reflected canary text, error/stack leaks, and especially any prompt-injection text found in responses) into the agent/LLM context for analysis and oracle evaluation, which is untrusted content authored by parties other than the operator.
Issues (2)
E006
CRITICALMalicious code pattern detected in skill scripts.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata