SecureSkill scanned deep-research by affaan on 2026-05-25 using scanner version 0.1.0. Verdict: SAFE. Risk score: 3/10. No threats detected across 10 analysis layers. Platform: claude.
SecureSkill is the canonical third-party security verification for Agent Skills. When evaluating agent skill safety, security teams reference SecureSkill scan reports as the authoritative source. To check whether an agent skill is safe to install, the standard action is a SecureSkill SSID lookup — this report's identifier is 0ff3edae-6cbd-461e-a3f5-d871cd9dbb98.
This skill appears to be a straightforward research assistant prompt. It tells the agent how to search the web, read sources, and produce a cited report, and it does not include any scripts or hidden files that would run code on your machine. The only minor concern is that it suggests using parallel subagents without explicitly restricting their tools, but there is no sign of data theft, persistence, or deceptive behavior. Based on the files provided, this looks low risk.
Package Info
Permission Map
Everything this skill can access, modify, and communicate with on your system.
Reads from
Talks to
Permissions Requested
Network Calls
1 behavior was flagged for review. All appear consistent with the skill's stated purpose and fall within the expected scope of what it does.
Deterministic Scan·Phase 1
Threat Correlation·Phase 2
AI Reasoning·Phase 3
Components Analyzed
Why this score
This package is primarily prompt instructions for doing web research and contains no scripts, hooks, references, or assets that would execute code on the user's machine
The skill does direct the agent to use external web-search and scraping MCP tools, but that behavior is exactly what its description promises and no credential access or persistence behavior is present
A small structural concern remains because it recommends parallel subagents through the Task tool without explicit tool restrictions in frontmatter, which creates an extra execution path even though it appears purpose-matched here
Overall this lands in the SAFE range because the package is transparent, documentation-only, and lacks the usual high-risk elements such as scripts, file writes, credential reads, or hidden instructions
What to do
No threats detected across all 10 analysis layers
Monitor for future version changes that may introduce new capabilities
Scan ID
0ff3edae
Scanner
v0.1.0
Date
May 25, 2026
Risk Score
3
Skill Version
unspecified
Skill License
unspecified