ptlam-creating-adr
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external documentation and project files to generate records and explanations.
- Ingestion points: Reads existing ADRs, feature specifications, and repository evidence (referenced in
SKILL.mdandskills/ptlam-creating-adr/SKILL.md). - Boundary markers: The skill employs strict schemas (e.g.,
references/adr-schema.md) to structure output, providing logical delimiters for the generated content. - Capability inventory: The skill is capable of writing new Markdown files to the
<project-root>/docs/adr/directory. It does not perform network operations or execute arbitrary shell commands. - Sanitization: While the skill does not explicitly detail input sanitization, the generation process is constrained by specific templates and a verification gate that ensures output matches the source evidence.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform syntax and rendering checks on Mermaid diagrams using tools available in the project environment. These instructions are limited to verifying diagram validity and do not involve arbitrary command execution or system modification.
- [DATA_EXFILTRATION]: No network operations or credential harvesting patterns were identified. The skill's file operations are limited to reading project context and writing documentation to defined paths within the project root.
Audit Metadata