harness-enable-circuit-breaker
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external task tracking files and global state files to monitor execution metrics.
- Ingestion points: Reads content from .EnjoyHarness/ITERATION_COUNTER.md, .EnjoyHarness/GLOBAL_STATE.md, and .EnjoyHarness/.task-*.md in SKILL.md.
- Boundary markers: Absent. No delimiters are used to protect against instructions embedded in task data.
- Capability inventory: Utilizes Bash for command execution and Write/Edit tools for file system modifications.
- Sanitization: Absent. Relies on simple text filtering (grep, awk) for value extraction.
- [COMMAND_EXECUTION]: The skill uses Bash scripts to perform state monitoring and manage safety flags.
- Evidence: SKILL.md contains multiple shell script blocks using grep, awk, sed, and file redirection to check thresholds and update the .EnjoyHarness/ directory.
Audit Metadata