52-mobile-animation
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown-based instructions for a frontend engineer. It does not include any scripts, external dependencies, or network-enabled commands. The instructions focus on performance, accessibility, and standard development lifecycles.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent must ingest and analyze untrusted data from the local repository and user requirements. (1) Ingestion points: Existing repository code, framework configurations, and user requirement descriptions in SKILL.md. (2) Boundary markers: None identified; the instructions do not include specific delimiters or warnings for the agent to ignore instructions embedded in the analyzed code. (3) Capability inventory: The agent is expected to perform repository inspection and implementation, implying read/write access to project files. (4) Sanitization: None; the skill does not instruct the agent to sanitize or validate content found during the inspection process.
Audit Metadata