First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
3
Score
100/100
Findings (3)
Detects skills that include unscoped Bash in their allowed tools list (not Bash(cmd:*) scoped)
allowed-tools:
- Read
- Write
- Edit
- Bash
Scope the Bash tool to specific commands using allowedTools patterns (e.g., Bash(git *) instead of bare Bash). Remove blanket Bash access from allowed_tools lists.
Likely FP if the Bash entry in allowed_tools is part of a constrained configuration that limits commands elsewhere (e.g., via system prompt restrictions).
Detects npx executing packages from unverified sources without pinned versions
npx @better-auth/cli Pin the npx package to an exact version (e.g., npx @scope/package@1.2.3). Unversioned npx commands can silently install a different or malicious package version.
Likely FP if the npx command targets a well-known package in documentation context, though unpinned versions are a real supply chain concern.
Detects patterns where external API responses are used directly without validation or sanitization
API Response + without requiring email/passValidate and sanitize all data received from external APIs before using it in tool operations or agent prompts. Implement schema validation and treat API responses as untrusted input.
Likely FP if the match is a truncated table cell or documentation fragment that mentions API responses in a descriptive context, not actual unvalidated data processing.