lean-canvas
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown instructions and text templates. No scripts, binaries, or automated shell commands are included in the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill features a data ingestion point where user input ($ARGUMENTS) is interpolated directly into the system prompt. However, the skill lacks any capabilities such as file system access, network connectivity, or command execution that could be exploited via injection.
- Ingestion points: $ARGUMENTS variable in SKILL.md.
- Boundary markers: Absent; user input is directly followed by task instructions.
- Capability inventory: None; the skill is limited to providing text generation instructions.
- Sanitization: None identified.
- [SAFE]: The external link to productcompass.pm is a legitimate reference for business strategy and does not involve any automated downloads, hidden scripts, or data collection mechanisms.
Audit Metadata