Skip to content

Pull requests: NVIDIA/SkillSpector

New pull request New
32 Open 8 Closed
32 Open 8 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix(docker): install git for repository scans
#78 opened Jun 15, 2026 by medhdj Loading…
feat(analyzer): detect skills snooping on the agent ecosystem (other skills, MCP config, agent memory)
#77 opened Jun 15, 2026 by CharmingGroot Loading…
1
feat: implement dynamic analyzer discovery and risk score validation
#74 opened Jun 15, 2026 by umran666 Loading…
Add pre-commit hook, GitHub Actions workflow, and community templates
#73 opened Jun 15, 2026 by ckdash-git Loading…
2 of 5 tasks
1
fix(analyzer): parse structured output from text so OpenAI-compatible endpoints don't crash LLM analysis
#71 opened Jun 15, 2026 by bmd1905 Loading…
1
fix(meta-analyzer): keep LLM-confirmed findings when model returns end_line
#70 opened Jun 15, 2026 by JiayingHuang Loading…
feat(analyzer): detect anti-refusal statements (jailbreak preamble)
#65 opened Jun 15, 2026 by ankushchadha Loading…
1
feat(analyzer): detect SSRF (cloud metadata / internal-network / dynamic-host requests)
#63 opened Jun 15, 2026 by CharmingGroot Loading…
1
security(meta_analyzer): preserve high-severity static findings from LLM suppression
#54 opened Jun 14, 2026 by AbhiramDwivedi Loading…
1
ci: add GitHub Actions workflow (lint, unit tests, DCO)
#53 opened Jun 14, 2026 by AbhiramDwivedi Loading…
1
feat(providers): add claude_cli and codex_cli agent-CLI providers
#52 opened Jun 14, 2026 by AbhiramDwivedi Loading…
1
docs: document the integration contract and trust model
#51 opened Jun 14, 2026 by AbhiramDwivedi Loading…
1
docs: correct stale analyzer status and dangling references
#50 opened Jun 14, 2026 by AbhiramDwivedi Loading…
1
fix: ignore structural markdown comments in static engine
#49 opened Jun 14, 2026 by Rachitrajvaishkiyar Loading…
Use OpenAI default model for OpenAI fallback
#46 opened Jun 14, 2026 by sjh9714 Loading…
1
Reject invalid skill paths
#45 opened Jun 13, 2026 by fallintoplace Loading…
@
#41 opened Jun 13, 2026 by Sylviali-Maker Loading…
Trojan Source (CVE-2021-42574) bidirectional control characters in file contents were undetected
#40 opened Jun 13, 2026 by asadbekXodjayev Loading…
feat(mcp): expose SkillSpector as an MCP server with a scan_skill tool
#36 opened Jun 13, 2026 by CharmingGroot Loading…
fix(llm): isolate Stage 2 batch failures and keep unanalysed findings
#32 opened Jun 12, 2026 by nyxst4ck Loading…
docs: fix provider registry path
#30 opened Jun 12, 2026 by CooperSheroy Loading…
1
Fix(llm): retry transient failures and make concurrency configurable
#29 opened Jun 12, 2026 by jhamze7 Loading…
1
1
fix(supply-chain): exclude pyproject metadata keys from dependency extraction
#28 opened Jun 12, 2026 by CharmingGroot Loading…
1
1
fix(mcp): treat allowed-tools as a permission declaration for LP3
#27 opened Jun 12, 2026 by CharmingGroot Loading…
1
Detect whitespace padding used to hide prompt-injection instructions (P9)
#24 opened Jun 11, 2026 by korjavin Loading…
ProTip! Follow long discussions with comments:>50.