vigil
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-supplied data from the
{{args}}placeholder and passes it directly to sub-skills without sanitization or boundary markers. - Ingestion points: User input enters the skill context through the
{{args}}variable in SKILL.md. - Boundary markers: There are no delimiters or instructions to the agent to treat the input strictly as data, increasing the risk that malicious instructions in the arguments could be executed by the sub-skills.
- Capability inventory: The skill environment is configured with powerful tools including
Bash,Write, andWebFetch(as seen in the frontmatter), which could be leveraged if an injection is successful. - Sanitization: No validation or filtering is applied to the input before it is used to invoke subsequent tools or skills.
Audit Metadata