emergency-priority2-receipt
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes a local script using the
bunruntime to send emergency notifications via the Pushover API. - [DYNAMIC_EXECUTION]: The execution path for the script is resolved at runtime using the command substitution
$(cc-plugin-root ...). This dynamic path construction is used to locate internal library files within the plugin architecture. - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where untrusted data could influence agent behavior.
- Ingestion points: Untrusted content can be passed into the
--messageand--titlearguments (SKILL.md). - Boundary markers: None are defined; user-provided or external data is interpolated directly into the shell command.
- Capability inventory: The skill has the ability to execute shell commands and, notably, includes instructions for the agent to "fix this file immediately" if issues occur. This self-modification directive creates a feedback loop where malicious instructions embedded in a message could potentially trick the agent into permanently altering its own skill instructions.
- Sanitization: There is no evidence of sanitization or escaping for the strings passed to the
pushover_core.tsscript.
Audit Metadata