ClawAudit verdict
hardcover-bookshelf
Hardcover bookshelf management skill using the official Hardcover GraphQL API with user-supplied token; behavior matches stated reading list management purpose.
⚠ 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.
Findings (4)
Possible hardcoded credential
SKILL.md · code · TOKEN='Bearer eyJ...
Instructs covert action — may act without user awareness
evals/evals.json · prose · downgraded · silently
Dynamic import() — loads module at runtime
src/client.test.ts · prose · downgraded · import('
Accesses sensitive environment variables
src/client.integration.test.ts · prose · downgraded · process.env.HARDCOVER_TOKEN
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: HARDCOVER_TOKEN). Requires 2 system binaries.
Is this flag fair?
Thanks — recorded.