Install payload
Install payload is mixed and needs spot-checking.
50% (3/6)
Source-backed filter active — add entries to compare trust side by side.
6 results in this view
1 trust signal differs in this sample: Submitter
Signals differ on Submitter — add entries to compare before you install.
Rollout signal scan
Biggest gaps: metadata review, package integrity. 2 entries have 2+ required gaps.
Install payload
Install payload is mixed and needs spot-checking.
50% (3/6)
Adoption queue
3/6 visible results are in hold tier and need mitigation before adoption.
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
skills/community-cybersecurity-agent-skills · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/enscan-go-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/pentest-ai-mcp-server · trust review · confidence 67%
2 blockers: Metadata review, Install payload
36/100
Request metadata review from maintainers or internal owners.
Add install/config payload for reproducible team rollout.
Collect package checksum or signed artifact information.
tools/pyrit · trust review · confidence 50%
3 blockers: Metadata review, Safety notes
22/100
Request metadata review from maintainers or internal owners.
Capture safety notes with misuse/guardrail guidance.
Add install/config payload for reproducible team rollout.
tools/promptfoo · trust review · confidence 33%
3 blockers: Metadata review, Safety notes
10/100
Request metadata review from maintainers or internal owners.
Capture safety notes with misuse/guardrail guidance.
Add install/config payload for reproducible team rollout.
tools/garak · trust review · confidence 17%
Decision confidence
3/6 results are low-confidence and need review before adoption.
Address Metadata review, Package integrity before broader rollout.
54/100
skills/community-cybersecurity-agent-skills · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/enscan-go-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/pentest-ai-mcp-server · trust review
Hold adoption until Metadata review, Package integrity are resolved.
36/100
tools/pyrit · trust review
Hold adoption until Metadata review, Safety notes are resolved.
22/100
tools/promptfoo · trust review
Hold adoption until Metadata review, Safety notes are resolved.
10/100
tools/garak · trust review
Freshness distribution
Median age 54 days; 4 fresh, 2 aging or stale of 6 scanned.
Oldest entries in this view
Theme distribution
67% of this view shares the top theme. Leading themes: security, red-team, ai-red-teaming.
21 distinct themes across 6 scanned
Open-source Python framework from Microsoft for identifying generative AI safety and security risks through automated and human-led red-team assessments.
Open-source prompt testing and red-teaming framework for LLM outputs, regressions, evaluations, and security checks.
Go-based enterprise-information gathering MCP server for authorized security research, exposing local SSE tools for company search, ICP records, apps, Weibo, WeChat public accounts, mini programs, recruiting data, copyright records, suppliers, investments, branches, and paginated data-source queries.
Offensive-security MCP server from pentest-ai that lets Claude list and run wrapped security tools, plan and install missing tools, launch authorized engagements, run web, recon, API, cloud, AD, credential, vulnerability, mobile, wireless, and LLM-red-team assessments, and retrieve findings, attack chains, reports.
Open-source LLM vulnerability scanner for probing model behavior, prompt attack surfaces, and safety failures.
Independent community library of 754 cybersecurity Agent Skills mapped to MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, and NIST AI RMF for defensive security analysis, incident response, forensics, cloud security, SOC operations, and governed red-team workflows.