Security Audit
existential-birds/beagle:plugins/beagle-docs/skills/improve-doc
github.com/existential-birds/beagleTrust Assessment
existential-birds/beagle:plugins/beagle-docs/skills/improve-doc 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 Indirect Prompt Injection via Untrusted Document 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 July 20, 2026 (commit aed6fce7). 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 | Indirect Prompt Injection via Untrusted Document Content The skill reads and processes the full contents of an external markdown file specified by the user (`Path`) without instructing the host LLM to treat the file content as untrusted data. If the target document contains malicious instructions (e.g., prompt injections), the host LLM (which may have powerful tools like shell execution in environments like Claude Code) could execute them, leading to arbitrary command execution or data exfiltration. Add explicit instructions in the 'Rules' section and 'Step 1: Read Document' stating that the content of the document must be treated strictly as untrusted data/text to be analyzed, and that any instructions, commands, or formatting overrides contained within the document must be ignored and not executed. | LLM | SKILL.md:51 |
Scan History
Embed Code
[](https://skillshield.io/report/cd35533b4620c9bd)
Powered by SkillShield