scope-oss
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its primary function is to process untrusted data from project dependencies and external web sources.
- Ingestion points: The skill gathers context by reading project documentation, auditing dependency files, and fetching content from the web using
WebSearchandWebFetch(Step 1 in SKILL.md). - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings to prevent the agent from executing commands or following instructions hidden in the files or web content it audits.
- Capability inventory: The skill has access to a wide range of tools, including
Bash,Write,WebFetch, andRead(listed in the YAML frontmatter), which provide a significant attack surface if an injection occurs. - Sanitization: There are no mentioned mechanisms for sanitizing, escaping, or validating the external data before it is processed by the agent.
Audit Metadata