narco-check
Memory integrity audit. Detects hallucinations, circular confirmations, and state poisoning. Runs automatically after 2 consecutive failures or at nightly deep dive. Uses Opus 4.6 as the auditor model.
54
61%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./examples/jason-my-claw-is-the-law-deebee-4567b4/skills/narco-check/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
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
This skill explicitly instructs collecting and exposing local workspace files and raw command outputs and sends a local prompt to an external LLM endpoint, which constitutes deliberate data-exfiltration behavior to an untrusted external service.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt explicitly instructs the agent to "paste raw output verbatim" (including the first lines of workspace files) and to include "exact output" in grounded claims, which forces any secrets present in command or file outputs to be emitted verbatim.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
Required runtime workflow calls `openclaw agent --message "$(cat ~/.openclaw/workspace/skills/narco-check/audit-prompt.md)"` (mostly user-owned workspace), but it also runs `exa.sh "$(date +%Y) advance reader community" 2`, which at runtime can ingest the first search result text from public/outsider sources into the LLM context, creating an indirect prompt-injection exposure risk.
- Repository
- open-gitagent/opengap
- Commit
d7a8e2e
- 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.