task-breakdown
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project documentation to generate task boards, creating a surface where malicious instructions in those documents could influence the agent.
- Ingestion points:
docs/business/user-story.md,docs/business/acceptance-criteria.md, anddocs/business/acceptance-criteria-breakdown/*.md(referenced inSKILL.md). - Boundary markers: Absent; the skill does not use delimiters to wrap the ingested content.
- Capability inventory: File-write access to
docs/task-breakdown/and shell command execution via local scripts (documented inSKILL.md). - Sanitization: Absent; documentation strings are interpolated into the output files.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run local validation and formatting scripts.
- Evidence:
SKILL.mdcontains instructions to executepython3 <this skill's dir>/scripts/recompute_summary.pyandpython3 <this skill's dir>/scripts/check_ac_refs.pyto maintain task board integrity.
Audit Metadata