draft-project-charter
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data.
- Ingestion points: The procedure in Step 1 directs the agent to read existing documentation, specifically proposals, emails, and briefs (SKILL.md).
- Boundary markers: Absent. The instructions do not define delimiters or provide warnings to disregard instructions potentially embedded in the source documents.
- Capability inventory: The skill is granted access to
Read,Write,Edit,Bash,Grep, andGlobtools. - Sanitization: Absent. The agent is directed to use content from external files to populate the charter template without filtering or validation steps.
- [COMMAND_EXECUTION]: The skill requests the
Bashtool in itsallowed-toolsmetadata. While the documented procedure only describes file creation and editing, the inclusion of a shell environment provides a vector for arbitrary command execution that is not required for the skill's stated purpose.
Audit Metadata