Caveat verdict
deepseek-balance
Accesses credentials AND writes files
The skill explicitly reads $ANTHROPIC_AUTH_TOKEN as a fallback and sends it as a Bearer token to api.deepseek.com — a third-party host — which is concrete exfiltration of Anthropic credentials to an external service.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
network_out
file_read+write
Findings (3)
Possible hardcoded credential
SKILL.md · code · API_KEY="${DEEPSEEK_API_KEY:-$ANTHROPIC_AUTH_TOKEN}
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
Pipe-to-python pattern — remote code execution risk
SKILL.md · code · curl -s -X GET 'https://api.deepseek.com/user/balance' -H "Authorization: Bearer
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C/F). 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_outfile_writecredential_access Thanks — recorded.