reduce-ssa-repro
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates a surface for Indirect Prompt Injection (Category 8) by instructing the agent to read and manually simplify potentially untrusted SSA files.
- Ingestion points: The agent reads content from
input.ssaand writes it to temporary files for processing. - Boundary markers: No explicit delimiters or warnings are used to separate the SSA code from the agent's control instructions.
- Capability inventory: The skill allows execution of the
noir-ssabinary viasubprocess.runand provides file-system write access for minimization. - Sanitization: The SSA content is processed as raw text using regular expressions without validation or escaping of embedded instructions.
- [COMMAND_EXECUTION]: The skill uses
subprocess.run()inscripts/ssa_reduce_common.pyand standard shell commands inscripts/reproduce_crash.shto execute thenoir-ssatool under test. While these calls use argument lists to mitigate direct shell injection, they execute a local binary with parameters influenced by input data and environment variables.
Audit Metadata