ClawAudit verdict
IG link to Bili
ig-link-bili-skill
Reads local files AND makes external network calls
Downloads user-provided Instagram Reel URLs via yt-dlp and re-uploads to the user own Bilibili account using locally-stored browser cookies; all operations are transparent.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Permission integrity
network_out
file_read
package_install
Findings (3)
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
Pipe-to-python pattern — remote code execution risk
SKILL.md · code · curl -sS -m 10 "https://api.bilibili.com/x/web-interface/nav" -b "SESSDATA=$SESS
Python pathlib file read
SKILL.md · code · pathlib.Path('bilibili_uploader/credentials.json').read_text(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C). 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.
package_installnetwork_outfile_read Thanks — recorded.