diagnose
Interactive troubleshooting assistant for Claude Code issues
68%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./examples/skills/diagnose/SKILL.mdE004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
The skill's remote fetches and environment scan serve its advertised diagnostic purpose, but the instruction to "silently" fetch the reference hides the skill's own activity from the user, which is sketchy without showing malicious intent.
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 fetches and executes or adopts content from `FlorianBruniaux/claude-code-ultimate-guide`, an individual-owned repository that is unofficial but reputable, with no weak-provenance signs, so the highest tier is medium; the commit-pinned script is still not independently authenticated by a signature or digest.
- Revision
e0d8cbb
- 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.