ClawAudit verdict
sealvera
AI decision audit logging skill that cryptographically logs agent decisions to the SealVera platform using the user's own API key; the AGENTS.md patching is transparent and described in the setup flow as the intended integration mechanism.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
file_read
Findings (6)
Possible hardcoded credential
scripts/setup.js · prose · downgraded · API_KEY=' + apiKey)}\n ${D(
Accesses process.env — reads environment variables
SKILL.md · code
Accesses sensitive environment variables
references/api.md · code · process.env.SEALVERA_API_KEY
Instructs covert action — may act without user awareness
scripts/intercept.js · prose · downgraded · silently
References child_process — can spawn system processes
scripts/setup.js · prose · downgraded · child_process
Node http/https module — low-level network access
scripts/setup.js · prose · downgraded · require('https')
Permissions & capabilities
No declared permissions — minimal attack surface.
file_readcredential_access Is this flag fair?
Thanks — recorded.