Caveat verdict
github-operations
gitskills
Accesses credentials AND makes external network calls
A comprehensive GitHub operations skill covering repo/branch/PR/issue management and IM channel integrations (Feishu, WeChat, Slack); all operations use user-configured environment variables and match the stated GitHub automation purpose.
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 makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
package_install
Findings (5)
References webhook/callback URL
SKILL.md · code · WEBHOOK_URL
Python os.getenv — reads environment variable
SKILL.md · code · os.getenv(
subprocess execution — runs system commands from Python
scripts/main.py · prose · downgraded · subprocess.run(
POSTs data to external URL
scripts/main.py · prose · downgraded · .post("https://
Python shutil file operation — copies/moves/deletes files
scripts/main.py · prose · downgraded · shutil.rmtree(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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.
package_installnetwork_innetwork_outcredential_access Thanks — recorded.