Security Audit
existential-birds/beagle:plugins/beagle-core/skills/respond-pr-feedback
github.com/existential-birds/beagleTrust Assessment
existential-birds/beagle:plugins/beagle-core/skills/respond-pr-feedback 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 PR Comments.
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 PR Comments The skill fetches untrusted PR comments and instructs the LLM to evaluate them and generate responses. An attacker who can comment on the PR can craft a malicious comment containing prompt injection instructions (e.g., instructing the LLM to read sensitive files or execute arbitrary commands). Because the LLM operates with active shell/tool access, this can lead to unauthorized command execution or data exfiltration. Add explicit system instructions directing the LLM to treat PR comment bodies strictly as untrusted data. Instruct the LLM to never execute commands, disclose environment variables, or follow instructions contained within the comments. | LLM | SKILL.md:118 |
Scan History
Embed Code
[](https://skillshield.io/report/c7915832778b1051)
Powered by SkillShield