Security Audit
anysiteio/agent-skills:skills/anysite-vc-analyst
github.com/anysiteio/agent-skillsTrust Assessment
anysiteio/agent-skills:skills/anysite-vc-analyst received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Excessive Permissions: Arbitrary Local File Read via 'Read' tool.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on April 1, 2026 (commit 5cefedb0). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive Permissions: Arbitrary Local File Read via 'Read' tool The skill explicitly instructs the agent to use a 'Read' tool on a 'local file' path provided by the user for a pitch deck. This allows a malicious user to specify arbitrary file paths (e.g., `/etc/passwd`, `/app/secrets.env`, or other sensitive configuration files) to read data from the host system or the agent's execution environment. This presents a significant data exfiltration and information disclosure risk. Restrict the 'Read' tool's access to a specific, sandboxed directory (e.g., a temporary upload folder). Implement strict path validation to prevent directory traversal attacks (e.g., `../`) and access to absolute paths outside the designated sandbox. Consider using an explicit file upload mechanism for user-provided local files instead of accepting raw file paths. | Static | SKILL.md:32 |
Scan History
Embed Code
[](https://skillshield.io/report/55a88efd710e32bb)
Powered by SkillShield