fancy-yard-landscaper
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to the processing of untrusted data through the WebFetch tool and photo analysis activities described in the instructions.\n
- Ingestion points: Untrusted data enters the agent context via external websites (through the WebFetch tool) and user-provided photos for yard analysis as described in SKILL.md.\n
- Boundary markers: The instructions lack explicit delimiters or safety instructions to prevent the agent from treating data content retrieved from external sources as executable instructions.\n
- Capability inventory: The skill is configured with access to high-privilege tools including Bash, Write, Edit, and WebFetch in the YAML frontmatter of SKILL.md.\n
- Sanitization: There are no documented procedures or instructions within the skill files to sanitize or validate content retrieved from external URLs or image metadata before it is processed by the LLM.
Audit Metadata