pm-aarrr
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's preamble section triggers the execution of a local shell script named 'check-update.sh' using a relative path that accesses parent directories.
- Evidence: 'bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true' in SKILL.md.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it interpolates external data into sub-agent prompts.
-
- Ingestion points: Reads from 'docs/02-方案设计/数据指标体系.md' and accepts user input via 'AskUserQuestion'.
-
- Boundary markers: Prompt templates for sub-agents do not utilize specific delimiters or instructions to ignore embedded commands.
-
- Capability inventory: The execution environment provides access to 'Bash', 'Write', 'Read', and 'Agent' tools.
-
- Sanitization: There is no evidence of data sanitization or escaping before the external content is processed by sub-agents.
Audit Metadata