error-detective
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external data, including stack traces and log files, which constitutes a potential attack surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The main instructions in
SKILL.mdand the utility scriptscripts/debug_helper.pyare explicitly designed to read and parse external log files and error reports provided by the user or extracted from the environment. - Boundary markers: The skill lacks explicit boundary markers or instructions directing the agent to ignore or isolate potential commands embedded within the text of the logs and stack traces being analyzed.
- Capability inventory: The skill utilizes file-reading and script execution capabilities to analyze these external data sources, placing the agent in a context where it interprets untrusted content.
- Sanitization: There is no evidence of content sanitization or filtering to remove potential prompt injection payloads from the ingested logs before they are processed by the agent.
Audit Metadata