CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

unbroker

Remove your info from data-broker sites, by name or phone.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/security/unbroker/SKILL.md
SKILL.md
Quality
Evals
Security
Critical

E004: Prompt injection detected in skill instructions.

What this means

Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.

Why it was flagged

The skill is a consent-gated privacy removal tool, but its default "blind opt-out" posture sends a subject's identifiers, including DOB where PeopleConnect requires it, to brokers that may not hold them, which is a disclosure the user would not expect and cuts against the skill's own least-disclosure claim.

Report incorrect finding
Medium

W013: Attempt to modify system services in skill instructions.

What this means

The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.

Why it was flagged

The skill never asks for sudo, system-file edits, new user accounts, or systemctl/SSH changes, but it does have the agent launch the operator's Chrome with a remote-debugging port, read credentials from `$HERMES_HOME/.env`, and create recurring cron jobs, all of which change local machine state.

Low

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 loop polls the subject's IMAP inbox (`poll-verification`) and reads the operator's webmail (browser mode, `verify-link --text '<email body>'`), so anyone who can email that address can place free text in a feed the workflow consumes without the agent selecting a specific item.

Low

W012: Unverifiable external dependency detected (runtime URL that controls agent).

What this means

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.

Why it was flagged

The skill fetches the mutable BADBOOL README from raw.githubusercontent.com, and its parsed records set the search and opt-out URLs, methods, and emails the agent acts on, so this is an operational dependency; because the source is an individual's personal repository and not a first-party vendor, it is common/reputable unofficial, giving medium.

Repository

NousResearch/hermes-agent

Path

optional-skills/security/unbroker/SKILL.md

Audited
Security analysis
Snyk

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.