fast-shot
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a decision-making framework that ingests external information and triggers actions, which introduces a vulnerability surface where malicious instructions in external data could influence agent behavior.
- Ingestion points: The skill explicitly processes
EXTERNAL_FACTandsupplied factsduring the 'Frame' and 'Ground' steps defined in SKILL.md. - Boundary markers: While the skill uses semantic labels to categorize data types, it lacks explicit technical delimiters or instructions to ignore embedded commands within external data.
- Capability inventory: The 'Decide, act, and deliver' section in SKILL.md instructs the agent to "perform the smallest authorized action" and "run the smallest authorized empirical operation," implying interaction with tools or shell commands.
- Sanitization: No explicit sanitization or validation logic for external inputs is specified in the instructions.
- [NO_CODE]: The skill consists entirely of markdown-based reasoning instructions and contains no executable scripts or package configurations.
Audit Metadata