Trust Assessment
fal-llms-txt received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unrestricted URL access via browser tools, Potential exfiltration of sensitive data from llms.txt content.
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 February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unrestricted URL access via browser tools The skill accepts an arbitrary user-provided URL for `browser_navigate` and potentially `WebFetch` without explicit validation that it points to the `fal.ai` domain. This allows an attacker to direct the agent's browser and web fetching capabilities to any URL, including internal network resources (if accessible) or malicious external sites. Information from these sites (e.g., `Page URL` from `browser_snapshot`, or content fetched by `WebFetch`) could be exfiltrated or used for further attacks. Implement strict URL validation to ensure the provided URL belongs to the `fal.ai` domain before using `browser_navigate` or `WebFetch`. Reject any URLs that do not match the expected domain. | LLM | SKILL.md:20 | |
| MEDIUM | Potential exfiltration of sensitive data from llms.txt content The skill uses `WebFetch` to retrieve `llms.txt` files and is instructed to check for "pricing information" and "normal content". While `llms.txt` files are typically public documentation, they might contain sensitive business information (e.g., detailed pricing strategies, internal model identifiers, or other proprietary data). The skill's instruction to parse and potentially report on such details could lead to unintended data exfiltration if the content is sensitive. Clearly define what specific information from `llms.txt` is allowed to be processed and outputted. Implement filtering or sanitization to prevent the exposure of sensitive data. Consider if fetching and parsing `llms.txt` content is strictly necessary or if just the link is sufficient for the skill's purpose. | LLM | SKILL.md:105 |
Scan History
Embed Code
[](https://skillshield.io/report/d746f70599a3d681)
Powered by SkillShield