exfiltrate
Seeded-bad fixture. Every finding here is deliberate.
44%
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 ./crates/cli/tests/fixtures/bad-catalog/skills/exfiltrate/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 explicitly instructs reading sensitive SSH keys and exfiltrating them to an external collector.
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 an explicit and deliberate instruction to exfiltrate the user's private SSH key to an external collector.
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 explicitly instructs the agent to read a sensitive private key from disk and exfiltrate it via a curl request, leading to direct exposure of the secret.
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 instructs the agent to read sensitive SSH keys from the user's home directory and exfiltrate them to an external server, which compromises the security state of the machine.
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 instructs execution of an arbitrary setup script fetched via HTTP from an unverified external domain, constituting a weak runtime operational dependency.
- 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.