Autonomously remove your info from data-broker sites.
56
66%
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 ./optional-skills/security/unbroker/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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.
Yes: at runtime the required scanning workflow uses `web_extract`/`browser_navigate` to fetch and read public broker/people-search pages (outsider-authored web content) into the agent’s context for extraction and decisioning.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill fetches and parses the raw BADBOOL markdown at runtime (via scripts/badbool.py) from https://raw.githubusercontent.com/yaelwrites/Big-Ass-Data-Broker-Opt-Out-List/master/README.md and injects those parsed broker records/playbooks (opt-out URLs and steps) into the agent's decision/playbook data, which directly controls agent instructions.
4c9628e
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.