docs-refresh
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from
.claude/skills/*/skill.yamlfiles to generate documentation, creating a surface for indirect prompt injection.\n - Ingestion points: Reads configuration data from
.claude/skills/using the Read and Glob tools as described in SKILL.md.\n - Boundary markers: There are no explicit markers or instructions to treat the ingested YAML content as untrusted data.\n
- Capability inventory: The skill utilizes Bash and Write tools, which could be leveraged if the agent follows instructions embedded in the source files.\n
- Sanitization: No sanitization or validation of the ingested content is specified before it is used to update CLAUDE.md.\n- [COMMAND_EXECUTION]: The skill executes shell commands using the
taskrunner to refresh documentation and validate skills.\n - Evidence: Commands such as
task docs:refresh,task docs:refresh-check, andtask claude:skills-referenceare used to perform the core functions of the skill.
Audit Metadata