github-code-review
Review PRs: diffs, inline comments via gh or REST.
55
63%
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
Fix and improve this skill with Tessl
tessl review fix ./skills/github/github-code-review/SKILL.mdLow
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
This skill’s required PR workflow fetches outsider-authored PR metadata/body via GitHub API (e.g., `pr['body']`) and lists/reads changed file contents from that PR; those readable texts flow into the LLM context during “gather PR context” and “read the diff/file-by-file” steps, enabling indirect prompt injection via the PR author’s free text.
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 issues runtime curl requests to GitHub API endpoints (e.g. https://api.github.com/repos/$OWNER/$REPO/pulls/$PR_NUMBER) to fetch PR metadata and bodies which are injected into the agent's context and therefore can directly influence prompts/behavior at runtime.
- Repository
- NousResearch/hermes-agent
- Commit
6a8d318
- 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.