autoskill Eval
==============

Status: failed
Score: 76/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Permission surface: secrets or environment access, shell or command execution

Install:
npx skills add K-Dense-AI/scientific-agent-skills --skill autoskill

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Good trust signals with a few areas worth checking before rollout.
- WARN Audit score: Needs review
- WARN Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: MIT license
- FAIL Permission surface: secrets or environment access, shell or command execution

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit score: Needs review
- Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- The skill depends on the screenpipe daemon and a SCREENPIPE_TOKEN; if the daemon is not running or the token is invalid, the skill will fail. Documentation covers this, but a more explicit error-handling section in SKILL.md could help.
- Cloud backends (Claude/Foundry) are optional but require the user to supply API keys; the skill does not perform additional runtime validation of the endpoint beyond the cleartext check, so a misconfigured (but HTTPS) remote endpoint could receive data. This is acceptable given the user explicitly configures it, but the documentation could emphasise the privacy implications more strongly.
- Permission surface needs review: secrets or environment access, shell or command execution
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- The skill depends on the screenpipe daemon and a SCREENPIPE_TOKEN; if the daemon is not running or the token is invalid, the skill will fail. Documentation covers this, but a more explicit error-handling section in SKILL.md could help.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Cloud backends (Claude/Foundry) are optional but require the user to supply API keys; the skill does not perform additional runtime validation of the endpoint beyond the cleartext check, so a misconfigured (but HTTPS) remote endpoint could receive data. This is acceptable given the user explicitly configures it, but the documentation could emphasise the privacy implications more strongly.
- Permission surface needs review: secrets or environment access, shell or command execution

URLs:
- Skill: https://www.openagentskill.com/skills/k-dense-ai-autoskill
- Audit: https://www.openagentskill.com/skills/k-dense-ai-autoskill/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=k-dense-ai-autoskill