long-range-continuity
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to execute a local script located at
../../scripts/long_range_continuity.pyfor deterministic state changes and validation. - [INDIRECT_PROMPT_INJECTION]: The skill processes external project data, creating an attack surface where malicious instructions could be embedded in data files.
- Ingestion points: Steps 1 and 2 in
SKILL.mddirect the agent to read../../references/LONG_RANGE_CONTINUITY.mdand the current durable project state. - Boundary markers: Absent; there are no instructions or delimiters defining the boundary between the data being read and the agent's instructions.
- Capability inventory: The skill possesses the ability to execute the
long_range_continuity.pyscript and write results back to the project state (Step 5). - Sanitization: Absent; the skill does not specify any validation or sanitization protocols for the data ingested from the reference files.
Audit Metadata