daily-ui-inspiration-capture
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands such as
git status,git add -f, andnode scripts/check-ui-inspiration-duplicates.mjs. The use ofgit add -fspecifically instructs the agent to override user-defined repository ignore rules in thearticles/directory. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes external, untrusted content from the web to generate builder prompts.
- Ingestion points: External data is fetched from landing pages via a browser tool (SKILL.md).
- Boundary markers: No delimiters or safety instructions are defined to separate untrusted external content from the agent's instructions.
- Capability inventory: The skill has permissions to write files and execute local scripts (SKILL.md).
- Sanitization: The instructions do not require sanitizing or escaping the captured web content before its use in generated prompts.
Audit Metadata