research-target-resolver
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input to resolve investment targets and subsequently uses these values to construct file system paths.
- Ingestion points: The
target phraseprovided by the user is used to define theticker-or-slugvariable inSKILL.md. - Boundary markers: None; the skill does not use delimiters to separate user data from instructions.
- Capability inventory: The skill instructs the agent to create and update files in the
research/targets/directory as described inSKILL.md. - Sanitization: No explicit sanitization or validation of the identifiers is mentioned beyond lowercase conversion, leaving a surface for potential path manipulation.
- [SAFE]: The skill instructions advise using primary and stable sources for verification, including SEC company pages and official investor-relations sites.
Audit Metadata