update-nanoclaw
Efficiently bring upstream NanoClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.
61
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/update-nanoclaw/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
W008: Secret detected in skill content (API keys, tokens, passwords).
What this means
Detected sensitive credentials directly embedded within the skill content, such as API keys, access tokens, private keys, or service-specific secrets. Secrets should never be hardcoded in plain text within skill instructions.
Why it was flagged
I found a high-entropy, literal API key in diagnostics.md that appears to be a real credential rather than a placeholder. The JSON contains "api_key": "phc_fx1Hhx9ucz8GuaJC8LVZWO8u03yXZZJJ6ObS4yplnaP" which is random-looking, long, and prefixed with "phc_" (commonly used by PostHog/PHC keys). This meets the definition of a secret (usable API key) and should be treated as sensitive. No other strings in the provided files meet the high-entropy secret criteria; other values are obvious placeholders (e.g., "<uuid>") or configuration examples.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill's Step 0a fetches and checks out the upstream skill files from https://github.com/nanocoai/nanoclaw.git at runtime (git fetch / git checkout upstream/<branch> -- .claude/skills/update-nanoclaw/), and the skill then re-reads and follows the updated SKILL.md, meaning remote content can change the agent's instructions.
- Repository
- nanocoai/nanoclaw
- Commit
641963c
- 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.