proposal-writer
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and templates. No scripts, binaries, or executable files are present.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs to generate proposal content, which represents a standard surface for indirect prompt injection. The risk is considered minimal as the skill lacks any dangerous capabilities.
- Ingestion points: User-provided discovery notes, prospect info, and solution details in SKILL.md.
- Boundary markers: Absent; user inputs are directly interpolated into the output template.
- Capability inventory: None; the skill does not use any tools, network access, or file system permissions in SKILL.md.
- Sanitization: Absent; no filtering or validation is performed on the input data.
- [SAFE]: No malicious patterns, obfuscation, or high-risk behaviors were detected.
Audit Metadata