ClawAudit verdict
code-security-audit
Fetches from network AND uses eval/Function
Comprehensive security auditing toolkit running local OWASP/dependency/secret scans using standard tools (npm audit, pip-audit, gitleaks, trufflehog); credential_access and network_out are for scanning the local codebase and fetching vulnerability databases, consistent with stated security audit purpose.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Receives external input AND executes processes — the shape of a command & control channel
LLM05 · LLM06 · ASI10
Accesses system credential store AND makes external network calls
LLM02 · ASI03
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Installs packages AND executes processes — opaque dependency chain with execution
LLM03 · ASI04
Permission integrity
network_out
package_install
Findings (11)
Uses eval() — can execute arbitrary code
SKILL.md · code · eval(
Dynamic Function constructor — equivalent to eval()
SKILL.md · code · new Function(
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
References child_process — can spawn system processes
SKILL.md · code · child_process
Uses exec() — may execute shell commands
SKILL.md · code · exec(
Accesses .ssh directory
SKILL.md · code · .ssh/
Popular HTTP library — network access
SKILL.md · code · axios
Uses spawn() — can execute external programs
scripts/security-audit.sh · prose · downgraded · spawn(
apt-get install — installs system packages
templates/security-audit.gitlab-ci.yml · prose · downgraded · apt-get install
Makes HTTP request to external URL
SKILL.md · code · fetch(`https://
pip3 install — installs Python packages at runtime
templates/security-audit.gitlab-ci.yml · prose · downgraded · pip3 install
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_inprocess_execdynamic_evalpackage_installnetwork_outcredential_accesscredential_store Thanks — recorded.