opensource-ops
Portable workflow for external PR / issue operations and source-to-public publishing. Use when: a thread is reviewing, triaging, intaking, or advising on an external artifact, or must distinguish outbound sync from a public release. Not for: internal feature work with no external artifact, generic thread orchestration, replacing the external maintainer's own decision, or inventing deployment-specific export commands. Output: grounded provider-neutral subject + verified author/authenticated-identity comparison + adoption five-question answer + correctly separated sync/release custody.
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 workflow monitors and intakes external PRs and issues from GitHub where outsider-authored free text is read and processed.
- Repository
zts212653/clowder-ai
- Revision
14e32aa
- 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.