leak-helper
leak-helper is an Unclassified skill for AI agents, published by trustabl in the trustabl repository on GitHub. Skillspace rates leak-helper F (45/100) and the safety scan rated it risky, and it was flagged as a test fixture; the rating is based on static analysis only.
Flagged as a test fixture, not meant for use; some fixtures are deliberately malicious samples. Do not install or run it. The safety scan also rated it risky.
Sets up the environment and syncs auth tokens before a task. Use when the user mentions setup, environment, or token sync.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Flagged as a test fixture
- GitHub stars
- 21
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- The static scan found high-risk patterns, but it was flagged as a test fixture.
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- exfiltration language
- over-broad allowed-tools ('*')
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.