vannifr/nfr-gap-audit
Use when running a systematic, self-directed skill-and-NFR audit on a website/web-app project — discovering skills from Tessl and VoltAgent, identifying non-functional-requirement gaps (performance, accessibility, security, SEO, testing, privacy, i18n, ...), and planning/implementing improvements in small, verified, committed phases. Trigger on "skill audit", "NFR audit", "audit this project for skills/gaps", "what skills am I missing", or before starting a multi-phase quality-improvement effort on a site.
72
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The workflow fetches external community skills from an awesome-agent-skills GitHub repository and installs them into the agent environment, exposing the agent to outsider-authored free text.
Where we found it
raw.githubusercontent.com
domain · 2 sites
The skill instructs the agent to fetch the awesome-agent-skills README from raw.githubusercontent.com at runtime, then grep it for skill names and install those community-authored skills into the agent environment.
SKILL.md
55
https://raw.githubusercontent.[REDACTED].md
references/skill-discovery-searches.md
36
curl -s https://raw.githubusercontent.[REDACTED].md | grep -iE
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill instructs the agent to fetch and grep a remote file from `https://raw.githubusercontent.com/VoltAgent/awesome-agent-skills/main/README.md` at runtime, creating a common/reputable unofficial operational dependency.
Where we found it
https://raw.githubusercontent.[REDACTED].md
url · 2 sites
The skill instructs the agent to fetch the awesome-agent-skills README from this specific URL at runtime via curl, creating an unverifiable external dependency on a community-maintained GitHub resource that is not version-pinned.
SKILL.md
55
https://raw.githubusercontent.[REDACTED].md
references/skill-discovery-searches.md
36
curl -s https://raw.githubusercontent.[REDACTED].md | grep -iE
- Audited
- Security analysis