privacy-filter
Use when the work-journal app asks which transcript utterances of an hour are bystander or personal non-work conversations to remove, and which spoken identifiers to redact.
70
88%
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
The canonical home for this skill is privacy-filter in chandler767/WorkJournal
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 required workflow processes local transcript files representing audio recorded around the user's laptop, which contain conversation text from unknown speakers.
- 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.