root-cause-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external descriptions of incidents or problems, which presents a potential vector for indirect prompt injection if the processed data contains malicious instructions.
- Ingestion points: The skill accepts user-provided input through the
argument-hint('[event or problem to investigate]') which is then processed using the defined RCA methodologies (SKILL.md). - Boundary markers: There are no explicit instructions or delimiters defined to separate user-provided data from the agent's instructions, nor are there warnings to the agent to ignore instructions embedded within the analyzed content.
- Capability inventory: The skill frontmatter allows the use of
Write,WebFetch, andWebSearchtools, providing a pathway for an injection to result in unauthorized file system changes or data exfiltration via network requests. - Sanitization: No mechanisms for sanitizing, escaping, or validating the input data are described in the instructions.
Audit Metadata