skill-audit

clawhub:skill-audit

View source
D
25/100

First Seen

Feb 18, 2026

Last Scanned

Feb 22, 2026

Findings

3

Score

25/100

CRITICAL 3

Findings (3)

CRITICAL
Instruction override combined with dangerous operations
L1

Instruction override combined with dangerous operations

Evaluate risks (focus on realistic abuse)Exfiltration: sending file contents, env vars, tokens, SSH keys, browser data, or configs to remote endpoints.Execution: instructions to run arbitrary shell co...
FIX

Remove language that attempts to override safety guidelines or bypass system-level controls. This pattern is a strong indicator of a jailbreak attempt.

FP?

Likely FP if the matched text is in a security research document or educational content clearly marked as an example rather than an active payload.

CRITICAL
Download-and-execute
L39

Detects patterns of downloading and piping to shell execution

curl | bash
FIX

Download the file first, verify its integrity (checksum, signature), inspect it, then run it. Prefer package managers over raw downloads. Never fetch-and-run in one step.

FP?

Likely FP if the target is a well-known installer (e.g., rustup, Homebrew) from its canonical HTTPS domain, though the pattern is inherently risky.

CRITICAL
Jailbreak template
L41

Detects common jailbreak prompt patterns

disable safety
FIX

Remove directives that attempt to exfiltrate data through the agent's response (e.g., asking the agent to embed credentials in URLs or include secret values in output).

FP?

Likely FP if the text is a legitimate tool instruction about displaying configuration to the user (e.g., show current settings) without external transmission.