audit-consumers
audit-consumers is a Codebase audits & code health skill for AI agents, published by atlanhq in the application-sdk repository on GitHub. Skillspace rates audit-consumers F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Audit every github.com/atlanhq/ consumer of application_sdk against a user-supplied check specification. Discovers consumer repos via `gh search code`, applies one or more named checks per repo (grep patterns anchored to SDK symbol usage), and produces a markdown report — including a coverage table listing every analyzed repo with its outcome (no-usage / no-findings / has-findings). Optionally raises migration PRs against consumer repos with confirmed findings. Use when proposing an SDK breaking change, removing a deprecated symbol, or proactively measuring the blast radius of a refactor before merging.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 27
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 62 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- High-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- executes shell/subprocess
- base64 decode (possible obfuscation)
Not checked yet
- Category is a classifier prediction; no model has read this skill 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.