launch-strategy
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local Python script located at scripts/launch_readiness_scorer.py to process and score launch checklists. The script is written using only standard Python libraries and performs local file reading of JSON data. It does not perform network operations or access sensitive system files.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by instructing the agent to ingest content from external local files, such as .claude/product-marketing-context.md and references/launch-frameworks-and-checklists.md.\n
- Ingestion points: Instructions in SKILL.md direct the agent to read marketing context and reference documentation to inform its responses.\n
- Boundary markers: Absent; the instructions do not define specific delimiters or warnings to ignore embedded instructions within the ingested data.\n
- Capability inventory: The skill has capabilities for local file reading and script execution.\n
- Sanitization: Content from markdown files is processed directly by the agent without specific validation or filtering.
Audit Metadata