company-radar Eval
==================

Status: failed
Score: 63/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Audit score: Risky

Install:
npx skills add Varnan-Tech/opendirectory --skill company-radar

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: Potentially useful, but at least one trust signal needs human inspection.
- FAIL Audit score: Risky
- FAIL Agent safety gate: This skill should not be selected by an agent without explicit human security review.
- PASS License clarity: MIT
- FAIL Permission surface: secrets or environment access, shell or command execution

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit risk risky exceeds max_risk=medium
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
- No explicit prompt-injection safety guidance: the skill directs agents to ingest web and social media content, which is untrusted, but does not instruct the agent to treat that content as data rather than instructions.
- The skill depends on multiple external opendirectory micro-skills and API keys; if those skills are not installed or platforms are inaccessible, some channels may not work as described.
- Twitter/X data collection is referenced through a skill, but API access and scraping reliability are not addressed, which could cause incomplete signal collection in practice.
- Financial research output is not financial advice; require human review before any live investment decision.
- This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.

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
- No explicit prompt-injection safety guidance: the skill directs agents to ingest web and social media content, which is untrusted, but does not instruct the agent to treat that content as data rather than instructions.
- No OpenAgentSkill engagement data yet
- Audit risk risky exceeds max_risk=medium
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing

URLs:
- Skill: https://www.openagentskill.com/skills/varnan-tech-company-radar
- Audit: https://www.openagentskill.com/skills/varnan-tech-company-radar/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=varnan-tech-company-radar