content-fix
Autonomous fixer for documentation content issues. Triggered by content_fix issues (documentation + fix labels) or @claude comments on those issues. Reads the issue, identifies affected files, applies fixes following Netwrix writing standards, and pushes a branch. A separate workflow step creates the PR. Asks clarifying questions if the request is ambiguous.
96
96%
Does it follow best practices?
Impact
96%
1.60xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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
Third-party content exposure detected (high risk: 0.95). At runtime the workflow uses `gh issue view ... --json title,body` and `gh api .../issues/$1/comments --jq '.[].body'`, which ingests outsider-authored issue body text and comments (public GitHub issue participants) into the agent’s context for extraction and decision-making.
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
Potentially malicious external URL detected (high risk: 0.80). The skill calls the GitHub API at runtime (via commands like "gh issue view $1 --repo $REPO" and "gh api repos/$REPO/issues/$1/comments", i.e. https://api.github.com/repos/$REPO/issues/$1 and https://api.github.com/repos/$REPO/issues/$1/comments) and uses the returned issue title/body and comments to directly determine and control what edits the agent will make, so this external content controls prompts/instructions.
- Repository
- netwrix/docs
- Commit
6b797b3
- 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.