ln-63-deployment-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its requirement to read and act upon external repository content.\n
- Ingestion points: The agent is instructed to read repository instructions, configuration files, and delivery conventions in SKILL.md.\n
- Boundary markers: The skill mentions using authorized tools and staying within granted scope, but lacks specific delimiters or 'ignore instructions' markers for the content it reads.\n
- Capability inventory: The skill has access to powerful capabilities including native build commands, IaC planning, and authorized provider CLIs and APIs as described in the Tool Routing section of SKILL.md.\n
- Sanitization: No specific methods for sanitizing or filtering instructions from ingested repository content are defined.
Audit Metadata