copilot-instructions-blueprint-generator
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill utilizes prescriptive directives within its prompt templates to guide the generation of configuration files. These instructions are functional and aimed at ensuring output consistency, rather than attempting to bypass safety filters or override agent behavior.\n- [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface because it requires the agent to ingest and analyze untrusted data from the codebase.\n
- Ingestion points: The agent is instructed to scan all files in the repository, including source code and configuration files, to identify versions and patterns (SKILL.md).\n
- Boundary markers: There are no explicit delimiters or specific 'ignore embedded instructions' warnings provided in the generated prompt for the analysis phase.\n
- Capability inventory: The agent using this skill is expected to perform file-read operations across the codebase and a file-write operation to create the copilot-instructions.md file.\n
- Sanitization: The skill does not describe or implement any specific sanitization or validation of the analyzed content before it is processed by the AI.
Audit Metadata