Repository Issue Activity (beta)

#324 OpenAI fallback graph uses active-provider model IDs

#318 [BUG] SC4 has no notion of version ranges: "^1.8.3" becomes an exact pin, and an unversioned dep gets the package's worst-ever advisory as CRITICAL

#315 claude_cli provider: concurrent temp-file collision on Windows drops most files from LLM analysis ([WinError 32])

#314 tests\unit\test_patterns.py identified as threat

#312 EA3 flags Apache-2.0 LICENSE boilerplate as scope creep (fires on 814/817 skills in one corpus)

#313 LP3 remediation advises adding a `permissions` field that Claude Code's SKILL.md schema does not have

#310 --baseline is silently ignored when scanning with --recursive

#200 [BUG] MCP server reports llm_available=false and skips the LLM pass when only the OpenAI fallback credential is set

#271 Publish SkillSpector to PyPI for easier installation and integration

#304 [BUG] OpenAI-compatible provider + Gemini: report issues have null 'finding' and 'category' (explanation/severity OK)

#303 [BUG] Rate-limited providers silently lose analyzer coverage: max_concurrency=10 hardcoded, 429 batches dropped without retry, partial LLM pass not flagged

#300 LP1/LP3 remediation points at a `permissions` field that the Agent Skills spec does not define

#296 [Feature] Bound the cost of an LLM scan: --max-llm-calls / --llm-token-budget, and --estimate before spending

#297 P2 "Hidden Instructions" rule produces false positives due to missing word boundary on GET

#295 [BUG] claude_cli provider omits --setting-sources=, so the spawned claude runs the user's hooks (4 LLM calls -> 3h09m CPU, 1225 hook sessions)

#290 Deep scan can report SAFE when provider is unavailable

#294 [BUG] requirements.txt: any version specifier is treated as an exact pin (pillow>=10.0.0 reported as pillow==10.0.0 with its CVEs)

#281 AnthropicProvider ignores ANTHROPIC_BASE_URL (proxy/gateway endpoints bypassed)

#274 github releases + changelog

#283 [Feature] Configurable reasoning effort for LLM analysis

#284 Clarify MAX_FILE_BYTES character-based size limit

#278 Auto-discover a shipped baseline so distributed skills carry their own suppressions

#221 docs: add OWASP Agentic Skills Top 10 (AST10) coverage matrix and gap analysis

#8 Support Github Copilot LLM as a provider

#277 Add your HVTrust badge to the README?