References external URL — review for indirect prompt injection risk
Vettd coreOWASP LLM03External URL(s) detected in SKILL.md — referenced content can change after audit
llama.cpp local GGUF inference + HF Hub model discovery.
This skill includes a SKILL.md descriptor and ships with reference documentation. Security observation: references external URL.
Vettd Verdict
The overall verdict combines pass, warning, and failure signals across our checks. Click to see how each check is computed.Skill has warnings: 1 warning in security or structure checks.
Link points to the repository’s default branch (current HEAD). Certification reflects the state of the repo on Jul 2, 2026. Scanned at 30e947e0.
/ coming soon
/ coming soon
/ coming soon
/ coming soon
security
External URL(s) detected in SKILL.md — referenced content can change after audit
Scanned text content for instruction override, jailbreak framing, credential solicitation, and embedded injection markers
No repository field found in SKILL.md frontmatter. Skills without a verifiable source repository cannot be externally audited.
Scanned all files for credentials, private keys, and code-level risks (eval, shell exec, destructive ops)
best practices
Found code blocks, input/output samples, or an examples section — concrete samples help agents pattern-match effectively
SKILL.md body references files in references/, scripts/, or assets/ — agents can load additional context on demand instead of consuming everything upfront
237 lines (recommended: under 500)
Structured procedures improve reliability for complex tasks
description
Add context like "Use this skill when..." to help agents know when to activate it
56/1024 characters used
evals
Add an evals/ directory with test prompts and expected outputs to measure skill quality
structure
Consider bundling reusable scripts for validation and automation
Additional documentation files available for progressive disclosure
Required skill definition file found
Name "llama-cpp" follows spec (lowercase, hyphens, ≤64 chars)