css-styling-expert
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local file system and tool outputs which could potentially contain malicious instructions.\n
- Ingestion points: Reads project source files in src/, package.json, and .browserslistrc using Read, Grep, and Bash. It also parses JSON output from npx lighthouse.\n
- Boundary markers: The instructions do not define delimiters or specific warnings to the agent to ignore instructions embedded within the source files or tool data.\n
- Capability inventory: The skill possesses Edit, MultiEdit, and Bash tools, allowing it to modify project code and execute shell commands based on the data it processes.\n
- Sanitization: There is no evidence of content validation, escaping, or filtering for the external data ingested into the agent's context.
Audit Metadata