software-instrumentation
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions involve the agent writing, reviewing, or modifying software code, which creates a surface for indirect prompt injection if the code being processed contains malicious instructions.
- Ingestion points: The agent context receives untrusted data in the form of existing source code or requests to generate new code based on user specifications (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined within the skill to isolate user-provided code or warn the agent to ignore instructions embedded in the code it reviews.
- Capability inventory: An agent using this skill is expected to have file-writing and code-modification capabilities to implement the recommended instrumentation.
- Sanitization: The skill does not specify sanitization or validation methods to ensure that comments or strings within the code being instrumented do not influence the agent's behavior.
Audit Metadata