mirror of
https://github.com/prompt-security/clawsec.git
synced 2026-06-13 05:28:02 +03:00
1e48a955cc
* fix(release): exclude tests from skill payloads * fix(release): normalize test path filtering * fix(release): prefer GitHub artifacts for non-OpenClaw installs * fix(release): keep legacy ClawHub publishing * fix(release): address skill packaging review feedback * chore(skills): bump release versions * feat(skills): surface recommended platforms * docs(skills): add signed release verification * fix(skills): normalize PR version bumps --------- Co-authored-by: David Abutbul <David.a@prompt.security>
Hermes Traffic Guardian
Baseline skill for Hermes runtime traffic monitoring.
This package is intentionally a spec scaffold. Builders should add the Hermes-specific monitor implementation here while preserving the safety contract in SKILL.md and SPEC.md.
Intended Capability
- detect outbound secret exfiltration in Hermes HTTP/HTTPS traffic
- detect inbound command-injection and tool-abuse payloads
- write redacted local JSONL findings
- export monitor posture for
hermes-attestation-guardian - provide explicit start, stop, status, and log-query commands
Builder Notes
Keep runtime ownership in this skill. hermes-attestation-guardian should only attest this skill's state, config, and output fingerprints.