lov-style-clone
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (sample articles) to extract style profiles and then performs file-writing operations. This creates an attack surface where instructions hidden within sample articles could potentially influence the agent's behavior.
- Ingestion points: User-provided sample and target articles collected in 'SKILL.md' Step 1.
- Boundary markers: Absent. The instructions do not specify using delimiters or warnings to ignore instructions embedded within the user data.
- Capability inventory: The agent uses the
Writetool to save profiles to the local filesystem (identified in 'SKILL.md' Step 4). - Sanitization: Absent. No logic is provided to sanitize or escape the content of the articles before processing or writing.
- [COMMAND_EXECUTION]: The skill instructs the agent to automatically write files to the local filesystem using the
Writetool by default. - Evidence: 'SKILL.md' Step 4 mandates archiving style profiles to
./output/style-profiles/without seeking user consent, which represents a default automated interaction with the host environment.
Audit Metadata