evolution-reporter
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill provides a mechanism to aggregate data from the local environment into reports, which creates a surface where the agent could potentially ingest and follow instructions embedded within the data it is processing.
- Ingestion points: The skill uses tools such as
Read,Glob, andGrepto ingest data from the ecosystem (referenced in SKILL.md). - Boundary markers: The provided report templates in SKILL.md do not include specific delimiters or warnings to the LLM to ignore instructions found within the data.
- Capability inventory: The skill allows for the use of powerful tools including
Bash,Write,Edit, andWebFetch. - Sanitization: There is no logic provided to sanitize or validate the content of the files being read before they are processed by the agent.
Audit Metadata