playbook
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from
blueprint/25-playbook.mdto update.wca-estado.json, creating a surface for indirect prompt injection. Maliciously crafted instructions in the blueprint file could potentially override the skill's intended behavior. - Ingestion points: The skill reads instructions and data from the file
blueprint/25-playbook.md(SKILL.md). - Boundary markers: None identified. There are no explicit instructions to the agent to treat the input data as potentially untrusted or to ignore embedded instructions within the file.
- Capability inventory: The skill is empowered to read local blueprint files and write modifications to the project's state file (
.wca-estado.json). - Sanitization: No input validation, escaping, or sanitization of the content from the blueprint file is described or performed.
Audit Metadata