dido-platform-docs-writer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository files (e.g.,
Dockerfile,scripts/,README.md) to generate its output. There is a risk that malicious instructions hidden within these files could influence the agent's behavior or be included in the final documentation as legitimate operational commands. - Ingestion points: Project manifest files (e.g.,
package.json,pyproject.toml), orchestration files (Dockerfile,compose.yaml), environment examples, and existing documentation within the repository being analyzed. - Boundary markers: The skill implements a manual "Discovery" and "Gate" review process to verify findings, but it does not specify technical sanitization or escaping for the content it extracts and interpolates into its output templates.
- Capability inventory: The skill is designed to read file contents and write new Markdown documentation files to the repository.
- Sanitization: While the instructions emphasize evidence-based documentation and forbid the copying of secrets, there is no mechanism to filter or sanitize potentially malicious code or instructions found in the source scripts or configuration files.
Audit Metadata