tidb-change-instruction-critic
Use when implementing a user- or reviewer-prescribed code change (including review comments with suggested fixes or options), especially when the requested edit may be risky, incomplete, ambiguous, or misaligned with TiDB correctness and compatibility constraints.
69
85%
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.
1 low severity finding. 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’s workflow explicitly relies on “review context” and “code/tests/review context” (step 2) and “review comments that include direct fix instructions” (Trigger), which are outsider-authored free text (e.g., PR/issue/discussion comments) that the runtime agent would ingest into the LLM context to perform the reconstruction and evaluation.
- Repository
- pingcap/tidb
- Commit
d8d57d7
- 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.