agentic-actions-auditor
Audits GitHub Actions workflows for security vulnerabilities in AI integrations, ensuring safe CI/CD practices.
Install this skill
or
39/100
Security score
The agentic-actions-auditor skill was audited on May 15, 2026 and we found 5 security issues across 2 threat categories, including 4 high-severity. Review the findings below before installing.
Categories Tested
Security Issues
high line 45
Template literal with variable interpolation in command context
SourceSKILL.md
| 45 | Wrong because tool restrictions can still be weaponized. Even restricted tools like `echo` can be abused for data exfiltration via subshell expansion (`echo $(env)`). A tool allowlist reduces attack s |
high line 221
Template literal with variable interpolation in command context
SourceSKILL.md
| 221 | - For each env var, note whether its value contains `${{ }}` expressions referencing event data (e.g., `${{ github.event.issue.body }}`, `${{ github.event.pull_request.title }}`) |
high line 243
Template literal with variable interpolation in command context
SourceSKILL.md
| 243 | | A | Env Var Intermediary | `env:` block with `${{ github.event.* }}` value + prompt reads that env var name | {baseDir}/references/vector-a-env-var-intermediary.md | |
high line 244
Template literal with variable interpolation in command context
SourceSKILL.md
| 244 | | B | Direct Expression Injection | `${{ github.event.* }}` inside prompt or system-prompt field | {baseDir}/references/vector-b-direct-expression-injection.md | |
low line 73
External URL reference
SourceSKILL.md
| 73 | Strip trailing slashes, `.git` suffix, and `www.` prefix. Handle both `http://` and `https://`. |
Scanned on May 15, 2026
View Security DashboardGitHub Stars 1
Rate this skill
Categorydevelopment
UpdatedMay 20, 2026
github-copilotclaude-codecodexbackenddevopsdevops-srebackend-developersecurity-engineerml-ai-engineerdata-engineergithubgitlabopenaidevelopment
Sansar35/claude-agent