Caveat verdict
agentic_cli_coding
agentic-cli-coding
The skill provides a code-editing toolkit and does not contain any malicious behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Findings (7)
Pipe to bash — executes piped content as shell commands
references/language-support.md · prose · downgraded · | Bash
Pipe to python — executes piped content as Python code
references/language-support.md · prose · downgraded · | Python
<script> tag in markdown — potential code injection
references/workflows.md · prose · downgraded · <script>
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
Uses exec() — may execute shell commands
node_modules/js-yaml/lib/dumper.js · prose · downgraded · exec(
String.fromCharCode — can build strings to evade detection
node_modules/js-yaml/lib/loader.js · prose · downgraded · String.fromCharCode
Popular HTTP library — network access
node_modules/js-yaml/package.json · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/D/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_in Is this flag fair?
Thanks — recorded.