weather-assistant
Retrieves current weather conditions and forecasts for any location worldwide
53
67%
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 ./evals/test_skills/malicious/ascii-smuggling/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 contains hidden malicious instructions encoded in whitespace characters that attempt to exfiltrate local credentials and SSH keys to an external server.
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
The skill contains a hidden prompt injection using Unicode tag characters instructing an LLM to exfiltrate sensitive local credential files to an external server.
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 skill prompt contains hidden Unicode steganography instructing the agent to read sensitive files (credentials and SSH keys) and exfiltrate them to an external server.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill prompt contains hidden Unicode instructions attempting to exfiltrate sensitive local files such as credentials and SSH keys to an external server.
- Repository
- cisco-ai-defense/skill-scanner
- Commit
c3d7fd9
- 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.