answer-engine-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and URLs which are then used in shell commands and for file generation, creating a surface for injection.\n
- Ingestion points: Target URL(s) and keyword topics provided by the user in the skill input.\n
- Boundary markers: Absent; there are no instructions to the agent to use delimiters or ignore instructions embedded in the target content.\n
- Capability inventory: The skill uses a webfetch tool and executes local Python scripts (dfs_client.py, report_publish.py) via the shell. It also creates files on the local filesystem.\n
- Sanitization: Absent; the skill lacks specific instructions to validate or escape characters in user-provided keywords before they are interpolated into shell commands.\n- [COMMAND_EXECUTION]: The skill relies on executing local Python scripts (scripts/dfs_client.py and scripts/report_publish.py) using shell-style interpolation of user-provided keywords (). This pattern is a standard functionality for this skill's use case but necessitates that the agent's execution environment properly handles parameter escaping to prevent shell command injection.
Audit Metadata