zig-docs
Fetches Zig language and standard library documentation via CLI. Activates when needing Zig API details, std lib function signatures, or language reference content that isn't covered in zig-best-practices.
83
82%
Does it follow best practices?
Impact
72%
1.50xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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 SKILL.md explicitly instructs the agent to fetch and parse public web content (curl raw files from codeberg.org and convert pages from ziglang.org and zig.guide with pandoc), so it ingests open third‑party documentation that the agent reads and uses to drive responses, enabling indirect prompt injection risk.
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 explicitly runs runtime fetches (curl/pandoc) against raw Codeberg and ziglang.org content—e.g. https://codeberg.org/ziglang/zig/raw/branch/master/lib/std/<module>.zig and https://ziglang.org/documentation/master/—and injects that fetched documentation into the agent's context to drive responses, so the external content can directly control prompts/outputs.
- Repository
- NeverSight/skills_feed
- Commit
2f57aec
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.