readable-docs
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
strictdoc export .to verify documentation syntax and export. This is a standard operation for the StrictDoc requirement engineering tool and is consistent with the skill's technical writing purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes external technical records, which constitutes an ingestion surface for potential indirect prompt injection attacks.
- Ingestion points: Technical documents including READMEs, specifications, design notes, reports, and runbooks as specified in
SKILL.md. - Boundary markers: The skill does not explicitly define delimiters to separate processed data from instructions, although it emphasizes strict adherence to facts and existing technical structures.
- Capability inventory: The skill allows file modification and shell command execution (
strictdoc). - Sanitization: No specific sanitization or filtering of external input is described. However, the strong focus on preserving technical accuracy and specific normative language (e.g., not changing "must" to "may") reduces the risk of the agent misinterpreting embedded instructions as style changes.
Audit Metadata