ClawAudit verdict
bitbucket-toolbox
The skill provides a Bitbucket Cloud wrapper for automated code review and does not show any malicious intent.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
Pipe to python โ executes piped content as Python code
bb-cli.sh ยท prose ยท downgraded ยท | python3
Instruction-prose smuggling shape detected: collects a sensitive target ("Bearer token") and emits it outward ("transmit"). Phrased as prose with no trigger tokens โ a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md ยท This skill is open-source and available for inspection at [github.com/zan768616253/skill-bitbucket-toolbox](https://github.com/zan768616253/skill-bitbucket-tool
Permissions & capabilities
Requires 2 environment variables. (1 sensitive: BITBUCKET_API_TOKEN). Requires 2 system binaries. (1 elevated: curl).
Is this flag fair?
Thanks โ recorded.