ClawAudit verdict
bria-ai
gal-test
Accesses credentials AND writes files
Bria.ai image generation and editing API skill that uses the user's own BRIA_API_KEY to call documented Bria API endpoints for legitimate image processing tasks.
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.
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
network_out
file_read+write
Findings (3)
Possible hardcoded credential
SKILL.md · code · TOKEN="$ACCESS_TOKEN
Writes to SKILL.md — self-modifying skill
SKILL.md · prose · downgraded · SKILL.md)** — Write
Base64 encoding/decoding
references/api-endpoints.md · code · BASE64_ENCODE
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: BRIA_API_KEY).
credential_accessnetwork_outfile_write Thanks — recorded.