ClawAudit verdict

video-bgm

phy-video-bgm

88
๐ŸŸข Trusted
Low risk โ€” reviewed by ClawAudit, behavior matches stated purpose

Accesses credentials AND makes external network calls

Analyzes a user's video with Gemini for mood detection and generates BGM via fal.ai Lyria2, then mixes audio with FFmpeg; credential_access for GOOGLE_GENAI_API_KEY and FAL_API_KEY is used transparently for the stated creative pipeline.

Automated static analysis โ€” not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence โ€” it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls โ€” potential credential theft

LLM02 ยท ASI03

Permission integrity

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

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime โ€” transitive dependencies are not auditable

package_install

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md ยท code ยท API_KEY="your_google_api_key

Pattern match medium

Python os.environ.get โ€” reads environment variable

SKILL.md ยท code ยท os.environ.get(

Pattern match medium

Python httpx request โ€” network access

SKILL.md ยท code ยท httpx.post(

Pattern match medium

POSTs data to external URL

SKILL.md ยท code ยท .post( "https://

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

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