ClawAudit verdict
signallink
The skill seems to be a webhook-to-telegram router, using its capabilities for a legitimate purpose. There is no clear evidence of malicious behavior.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
network_out
package_install
Findings (2)
Pipe to python โ executes piped content as Python code
.github/workflows/ci.yml ยท prose ยท downgraded ยท |
python
Python os.getenv โ reads environment variable
App/config.py ยท prose ยท downgraded ยท os.getenv(
Permissions & capabilities
Requires 2 environment variables. (1 sensitive: TELEGRAM_BOT_TOKEN). Requires 2 system binaries. (1 elevated: docker).
network_inpackage_installnetwork_out Is this flag fair?
Thanks โ recorded.