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.
28
22%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/continuous-learning-v2/SKILL.mdSecurity
3 findings — 2 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). The list contains multiple GitHub repo endpoints (which can host arbitrary code), an unencrypted HTTP config file, and critically a credential-embedded URL (https://ghp_xxxx@github.com/) — the presence of a leaked token/credential and plain-HTTP content are high-risk indicators, so treat these as suspicious and verify sources before downloading or executing anything.
E006: Malicious code pattern detected in skill scripts
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
Malicious code pattern detected (high risk: 1.00). The code intentionally sends local session observations to a remote LLM (via the claude CLI) for automated analysis and grants that remote model permission to write files directly into project storage without user confirmation, creating a clear channel for data exfiltration and remote-write/backdoor abuse (scrubbing is present but partial).
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: 0.75). At runtime, the observer-loop spawns `claude --print -p "$prompt_content"` where `prompt_content` includes `analysis_relpath` pointing to a temp file created from `tail -n ... "$OBSERVATIONS_FILE"`; that temp file contains project observations derived from Claude Code tool inputs/outputs (outsider-authored free text from other users/tools), which the LLM reads via the `--print` prompt.
- Repository
- affaan-m/everything-claude-code
- Commit
ec92b52
- 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.