Caveat verdict

Twitter Command Center (Search + Monitor)

asia-twitter-api-v1

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

The skill's own security notice explicitly warns that write operations require transmitting the user's Twitter email, password, and proxy to the third-party api.aisa.one, granting full account access 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.

33
security
70
transparency
70
maintenance

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.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-key

Pattern match low

Python urllib.request — network access

twitter_client.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

twitter_client.py · prose · downgraded · os.environ.get(

Pattern match low

Base64 encoding/decoding

twitter_client.py · prose · downgraded · base64-encode

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: AISA_API_KEY). Requires 2 system binaries. (1 elevated: curl).

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