gsd-docs-update
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves exploring the codebase directly to generate documentation, which introduces an indirect prompt injection surface.
- Ingestion points: The agent reads various codebase files using Glob, Grep, and Read tools as defined in SKILL.md.
- Boundary markers: The instructions in SKILL.md do not specify any delimiters or warnings to ignore instructions embedded within the codebase files.
- Capability inventory: The skill has access to Write, Edit, Bash, and Agent tools (SKILL.md), which could be leveraged if an injection occurs.
- Sanitization: No sanitization or filtering of the ingested content is mentioned in the skill definition.
- [COMMAND_EXECUTION]: The skill is configured with Bash tool access in the frontmatter. While this is likely intended for repository exploration, it provides a powerful interface that could be misused if the agent is influenced by malicious content.
- [DYNAMIC_EXECUTION]: The skill loads its core logic from a local execution context at ~/.claude/gsd-core/workflows/docs-update.md. This represents a dependency on vendor-provided local configuration files that are not contained within the skill's direct instructions.
Audit Metadata