asc-wall-submit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run the
asccommand-line tool. While this is the intended functionality of the skill, it involves executing shell commands with arguments provided by the user. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to command injection if the agent naively passes user-provided strings (such as the app ID, link, or name) to the shell without sanitization.
- Ingestion points: User-provided inputs for
app,link, andnameinSKILL.md. - Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the user data.
- Capability inventory: The skill executes shell commands (
asc apps wall submit) which could be manipulated if inputs contain shell metacharacters. - Sanitization: Absent; the instructions do not guide the agent to validate or escape the user-provided parameters before use.
Audit Metadata