Security Audit

anysiteio/agent-skills:skills/anysite-influencer-discovery

github.com/anysiteio/agent-skills

AI SkillCommit 5cefedb00ecc

CAUTION

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

anysiteio/agent-skills:skills/anysite-influencer-discovery received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Unrestricted Web Scraping Capability, Potential Data Exfiltration via Unsecured Export URLs.

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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unrestricted Web Scraping Capability The `webparser` tool, described as being able to `parse` 'any webpage', grants broad and unrestricted access to web resources. This capability could be exploited by a malicious user to prompt the LLM to access and potentially exfiltrate sensitive data from internal network resources (if accessible by the skill's execution environment), private user-specific URLs, or to perform reconnaissance on arbitrary external websites. The skill documentation does not specify any domain restrictions or sandboxing for this tool. Implement strict domain allow-lists for the `webparser` tool, or ensure it operates within a sandboxed environment with no access to internal networks or sensitive domains. Add explicit warnings about scraping private or internal URLs.	LLM	SKILL.md:290
HIGH	Potential Data Exfiltration via Unsecured Export URLs The `export_data` tool generates a 'download URL' for datasets that can include sensitive information such as 'Complete profile data', 'All posts with engagement', and 'Audience demographics'. The skill documentation does not specify the security measures (e.g., authentication, authorization, expiry, public/private access) applied to these generated URLs. If these URLs are not adequately secured, unauthorized parties could access and exfiltrate sensitive data. This risk is amplified when combined with the `webparser`'s ability to scrape arbitrary web content, which could then be exported. Clearly define and implement robust security measures for all generated download URLs, including strong authentication, fine-grained authorization, short expiry times, and ensuring URLs are not publicly discoverable. Document these security measures within the skill's capabilities.	LLM	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4b8ab7865b15e711.svg)](https://skillshield.io/report/4b8ab7865b15e711)