ylf-project-instructions
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary purpose is to maintain persistent project-level guidance by editing local documentation files. It does not contain any executable scripts, remote downloads, or hidden payloads.
- [SAFE]: The workflow incorporates defensive instructions for the agent, such as requiring target confirmation before editing and explicitly forbidding batch deletions or unrequested git actions.
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it reads project-controlled files (README.md, existing instruction files, and package scripts) to gather context.
- Ingestion points:
SKILL.md(Workflow Step 2) specifies reading existing project documentation and scripts. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious directions embedded in the files being read.
- Capability inventory:
SKILL.md(Workflow Step 4) indicates the agent is expected to verify changes using tests or representative script inputs, implying command execution capabilities. - Sanitization: No specific sanitization or filtering logic is defined for the content read from the project files.
Audit Metadata