report
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes potentially untrusted data from investigation and analysis tasks and interpolates it into a Markdown report template, creating a surface for indirect prompt injection.
- Ingestion points: The agent's current context containing research, debugging, or security audit results (SKILL.md).
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands in the data being summarized.
- Capability inventory: The skill is instructed to create directories and write Markdown files to the local filesystem (SKILL.md).
- Sanitization: No sanitization or escaping of the input content is performed before inclusion in the report.
- [COMMAND_EXECUTION]: The skill uses a shell command to ensure the target directory exists before writing the report.
- Evidence: The instruction
mkdir -p docs/reportsis executed to create the necessary directory structure (SKILL.md).
Audit Metadata