continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
60
—
Does it follow best practices?
Impact
—
No eval scenarios have been run
Critical
Do not install without reviewing
Security
2 findings — 1 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Suspicious download URL detected (high risk: 0.80). Several input URLs include embedded credentials (e.g., user:token or token-like strings) and an insecure HTTP download URL, which are high-risk patterns for credential leakage or tampering (possible malware distribution via compromised/unauthenticated hosts).
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.70). Yes—`agents/observer-loop.sh` reads the project’s `observations.jsonl` (populated from Claude Code hook JSON that includes tool inputs/outputs and user follow-ups) and injects that free-text content into the LLM via `claude ... --print -p "$prompt_content"` after `tail -n ... "$OBSERVATIONS_FILE" > "$analysis_file"`; those observations can contain outsider-authored text (e.g., tool outputs from external systems or other users’ messages) and are then ingested as readable prose for pattern analysis.
- Repository
- affaan-m/everything-claude-code
- Commit
4130457
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.