Caveat verdict

lobster-use

lobsterbio-use

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Bioinformatics analysis skill using the local Lobster CLI; credential_access reads one of the user-provided LLM provider API keys (Anthropic/Google/OpenAI/OpenRouter/AWS), all documented and consistent with the stated computational biology purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

50
security
20
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (1)

Pattern match critical

Pipe to python — executes piped content as Python code

references/agent-patterns.md · code · | python3

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_accesspackage_install

Is this flag fair?

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