ClawAudit verdict

content-safety-guard

phy-content-safety-guard

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Fetches from network AND uses eval/Function

Dual-layer AI output guardrail using Gemini Flash as a judge model; reads GOOGLE_GENAI_API_KEY from env for its stated purpose of evaluating AI-generated messages, with no exfiltration or deceptive behavior.

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.

0
security
60
transparency
70
maintenance

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.

Capability combination critical

Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)

LLM05 · LLM06 · ASI05

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Confirmed in code high

Dynamic import() — loads modules at runtime

SKILL.md · code

Pattern match high

Dynamic import() — loads module at runtime

SKILL.md · code · import("

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

Popular HTTP library — network access

SKILL.md · code · node-fetch

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.GOOGLE_GENAI_API_KEY

Confirmed in code low

fetch() — outbound network request

SKILL.md · code

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: GOOGLE_GENAI_API_KEY).

network_outpackage_installcredential_accessdynamic_eval
Check another skill Browse the registry Auditing your own skills or configs? Use the API