ClawAudit verdict

write-my-blog

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Self-hosted blog platform skill with a local Next.js server and REST API; all content is written to the user's own local database with no external exfiltration of credentials or content.

⚠ 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.

security

transparency

maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (5)

Pattern match high

Possible hardcoded credential

scripts/setup.sh · prose · downgraded · API_KEY="${SETUP_API_KEY:-}

Pattern match medium

Dynamic import() — loads module at runtime

platform/src/lib/cache/index.ts · prose · downgraded · import("

Pattern match medium

Uses exec() — may execute shell commands

platform/src/lib/cache/redis.ts · prose · downgraded · exec(

Pattern match low

Popular HTTP library — network access

platform/package-lock.json · prose · downgraded · node-fetch

Pattern match low

Accesses sensitive environment variables

platform/src/lib/auth/middleware.ts · prose · downgraded · process.env.API_KEY

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/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_outcredential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API