doc-sectest-validator
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the processing of external SECTEST documentation files. 1. Ingestion points: Markdown files located in docs/10_TSPEC/SECTEST/ and its subdirectories. 2. Boundary markers: The prompt instructions do not specify any boundary markers or delimiters to isolate document content from the agent's instructions. 3. Capability inventory: The skill utilizes tools to execute local scripts (validate_sectest.py, validate_all_tspec.sh, etc.) that perform file reading and writing (via the --auto-fix parameter). 4. Sanitization: No explicit sanitization or filtering of the processed documentation content is mentioned in the skill instructions.
- [COMMAND_EXECUTION]: The skill executes local framework scripts to perform validation tasks. Evidence: SKILL.md defines several commands that call python and bash to run scripts located in ai_dev_ssd_flow/10_TSPEC/scripts/ and ai_dev_ssd_flow/scripts/. These scripts are vendor-owned resources and do not require elevated privileges or access to remote resources.
Audit Metadata