ClawAudit verdict

heteromind

88
๐ŸŸข Trusted
Low risk โ€” reviewed by ClawAudit, behavior matches stated purpose

A natural language query routing system that connects to user-configured SQL/KG/table data sources using the user's own API keys; all external connections are to databases the user explicitly configures via environment variables.

โš  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.

18
security
40
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime โ€” transitive dependencies are not auditable

package_install

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md ยท code ยท api_key="sk-openai-key

Pattern match high

Uses exec() โ€” may execute shell commands

SECURITY.md ยท code ยท exec(

Pattern match medium

Python os.getenv โ€” reads environment variable

USAGE.md ยท code ยท os.getenv(

Pattern match low

Python aiohttp session โ€” async network access

src/engines/nl2sparql/multi_stage_engine.py ยท prose ยท downgraded ยท aiohttp.ClientSession

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

credential_accessnetwork_inpackage_install

Is this flag fair?

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