Hermes-only runtime security attestation and drift detection skill for operator-managed Hermes infrastructure.
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/hermes-attestation-guardian/SKILL.mdDetected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Several of the listed URLs point to non‑official/test hosts (example.test) and a generic GitHub releases download path that are capable of delivering archives/executables — these are higher-risk download vectors unless the consumer strictly enforces the signature+checksum verification shown in the repository.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The guarded advisory workflow reads outsider-authored free text from a remote/local advisory feed JSON (fetched via `globalThis.fetch` in `lib/feed.mjs` and then parsed/matched in `scripts/guarded_skill_verify.mjs` and `lib/attestation.mjs`).
prompt-security/clawsec
3ecb895
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.