deslop
Cut AI tells from prose people read: PR titles and bodies, Slack and Jira posts, READMEs and other human docs. Leave the fixed headings and bold labels of the `pr` skill and of PR templates as they are.
84%
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 skill instructs the agent to review and edit prose such as PR titles/bodies, Slack and Jira posts, and human docs, which can contain outsider-authored free text.
- Repository
aabuhijleh/abed-hub
- Revision
f9fe94c
- 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.