ClawAudit verdict
follow-github
Accesses credentials AND makes external network calls
GitHub digest skill that fetches activity from GitHub's API using a user-provided PAT stored locally; all network calls go to GitHub's own API and the skill explicitly tells users the token is never sent anywhere except GitHub.
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 makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
Findings (5)
Pipe-to-python pattern — remote code execution risk
SKILL.md · code · curl -s "https://api.telegram.org/bot<TOKEN>/getUpdates" | python
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
References agent configuration files
README.zh-CN.md · code · CLAUDE.md
Blob URL — may embed executable content
SKILL.md · prose · downgraded · blob:
Accesses sensitive environment variables
scripts/deliver.js · prose · downgraded · process.env.TELEGRAM_BOT_TOKEN
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C). 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: GITHUB_TOKEN). Requires 1 system binary.
credential_accessnetwork_out Thanks — recorded.