microcopy
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of Markdown and JSON metadata; it does not include any executable scripts, binaries, or configuration files.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data by instructing the agent to rewrite and review user-supplied UI text strings.\n
- Ingestion points: UI text samples (e.g., button labels, error messages, tooltips) provided in user prompts, as described in the examples and coverage sections of
SKILL.md.\n - Boundary markers: Absent; there are no instructions to use delimiters or "ignore embedded instructions" warnings for the user-provided content.\n
- Capability inventory: The skill is configured to use
ReadandGreptools (defined in theSKILL.mdfrontmatter) which allow for file system interaction.\n - Sanitization: Absent; no validation, escaping, or filtering of external content is defined in the skill logic.
Audit Metadata