agentic-process-monitor
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a protocol where an agent polls and reads data from files (
.status,.result) to determine its next steps. If the process generating these files handles untrusted input, it could allow for indirect prompt injection. - Ingestion points: Reading of
<step>.statusand<step>.resultfiles in the monitor directory (SKILL.md). - Boundary markers: The skill lacks instructions for using delimiters or warnings to ignore embedded instructions within these files.
- Capability inventory: The agent has access to
Bash,Read, andWritetools (SKILL.md frontmatter). - Sanitization: No input validation or sanitization of the file contents is described before the data is processed by the agent.
Audit Metadata