reflection-coach
Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change. Use for evidence-backed coaching proposals, never hot-swaps.
62
74%
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 ./packages/skills-catalog/catalog/bundled/paperclip-operations/reflection-coach/SKILL.mdLow
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
Reflection Coach ingests outsider-authored free text by pulling each target agent’s assigned issue bodies and comments via `GET /api/companies/.../issues?...` and `GET /api/issues/<issueId>` plus `GET /api/issues/<issueId>/comments`, where issue content and commenters are not first-party trusted by the threat model.
- Repository
- paperclipai/paperclip
- Commit
890ab9a
- 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.