affaan-m / agentshield
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
Why this job: says: security scanner; topics: security
What it does
- Replaces hardcoded secrets with ${ENV_VAR} references
- Tightens wildcard permissions (Bash(*) → scoped Bash(git *), Bash(npm *))
- runtimeConfidence is emitted for active runtime config, settings.local.json, docs/examples, installed Claude plugin caches, plugin manifests, and manifest-resolved non-shell hook code.
- harnessAdapters is local marker evidence only. It does not call external services or imply a hosted/team entitlement.
- Adapter confidence is strong when a primary harness marker exists, and partial when only supporting directories or secondary markers are present.
Get started
npx ecc-agentshield scan- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 1,382
- +24 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.6.0
- Released 2 months ago
- Built with
- TypeScript
- 99% of the code
Is it looked after?
- Contributors
- 7
- Last 90 days
- Issues
- 65% closed
- 17 still open
- Pull requests
- 90 merged
- 8 waiting
- Releases
- 6
- 6 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| snyk / agent-scan | 3,226 | 3 days ago | Apache-2.0 | Mac, Windows, Linux |
| AISecurityLab / hackagent | 535 | 7 days ago | Apache-2.0 | Mac, Windows, Linux |
More: languages, topics and project record
Languages
- TypeScript 99%
- HTML 1%
- Shell <1%
- JavaScript <1%
Topics
- ai-agent
- anthropic
- claude-code
- hackathon
- mcp
- opus
- security
Project record
- JobAI security
- StatusFeatured
- Commits221
- Forks307
- Watching11
- Stars in 28 days+107
- CreatedFeb 11, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026