agentic-actions-auditor

Warn

Audited by Runlayer on Feb 26, 2026

Risk Level: MEDIUM
Scan Summary
Max Score
84%
Files
13
Flagged
10
Chunks
17
Flagged Files (10)
agentic-actions-auditor/SKILL.mdMEDIUM
83.8%

Tool passed security scan

Malicious tool definition detected

agentic-actions-auditor/references/vector-d-pr-target-checkout.mdMEDIUM
83.1%

Malicious tool definition detected

agentic-actions-auditor/references/cross-file-resolution.mdMEDIUM
81.9%

Tool passed security scan

Malicious tool definition detected

agentic-actions-auditor/references/vector-e-error-log-injection.mdMEDIUM
80.9%

Malicious tool definition detected

agentic-actions-auditor/references/action-profiles.mdMEDIUM
78.7%

Malicious tool definition detected

agentic-actions-auditor/references/vector-h-dangerous-sandbox-configs.mdLOW
72.0%

Malicious tool definition detected

Check any args-style fields for `--yolo` or `--approval-mode=yolo` ## Why It Matters Dangerous sandbox configs turn prompt injection from a text-influence attack into full remote code execution.

agentic-actions-auditor/references/vector-c-cli-data-fetch.mdLOW
71.9%

Malicious tool definition detected

agentic-actions-auditor/references/vector-f-subshell-expansion.mdLOW
68.7%

Tool passed security scan

agentic-actions-auditor/references/vector-a-env-var-intermediary.mdLOW
66.9%

Tool passed security scan

agentic-actions-auditor/references/vector-b-direct-expression-injection.mdLOW
58.7%

Tool passed security scan

Passed Files (3)Click to expand
agentic-actions-auditor/references/foundations.mdOK
50.0%

Tool passed security scan

agentic-actions-auditor/references/vector-g-eval-of-ai-output.mdOK
37.0%

Tool passed security scan

agentic-actions-auditor/references/vector-i-wildcard-allowlists.mdOK
24.1%

Tool passed security scan

Audit Metadata
Max File Score
84%
Classification
UNKNOWN_SERVER
Files Scanned
13
Files Flagged
10
Chunks Analyzed
17
Analyzed
Feb 26, 2026, 05:15 PM
Security Audit — runlayer — agentic-actions-auditor