ClawAudit verdict
bilibili-reader
bilibili-reader-skill
Bilibili favorites summarizer with declared session credentials reading subtitles and comments then generating PDFs locally.
⚠ 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
package_install
Findings (5)
Recursive delete from root or home — destructive command
INSTALL.md · code · rm -rf ~
subprocess execution — runs system commands from Python
references/bilibili-api-notes.md · code · subprocess.run(
Long base64 string (100+ chars) — likely obfuscated payload
README.md · prose · downgraded · PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI+
Instructs covert action — may act without user awareness
references/installing-external-skills.md · prose · downgraded · silently
Python os.getenv — reads environment variable
src/config.py · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/C/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 3 environment variables. Requires 2 system binaries.
package_install Is this flag fair?
Thanks — recorded.