qodo-pr-resolver
Use when the user wants to review Qodo PR feedback or fix code review comments. Capabilities: view issues by severity, apply fixes interactively or in batch, reply to inline comments, post fix summaries (GitHub, GitLab, Bitbucket, Azure DevOps, Gerrit)
71
88%
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
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
Yes—Step 3/3b fetches Qodo review comments from the PR/MR via the provider CLIs/APIs (outsider-authored free text from the hosted code review thread), then Step 4 parses and uses the extracted “agent prompt”/issue text as LLM context/instructions.
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 fetches review comments (which include Qodo's "Agent Prompt" instructions that the resolver executes) from provider APIs such as "$GERRIT_URL/a/changes/<change-id>/comments" and "https://api.bitbucket.org/2.0/repositories/$BB_WORKSPACE/$BB_REPO/pullrequests/<pr-id>/comments", so remote content from those URLs directly controls agent behavior at runtime.
- Repository
- qodo-ai/qodo-skills
- Commit
5c63067
- 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.