pc-estimation
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of informational markdown files providing process guidance for project planning and estimation. There are no executable scripts, binaries, or automated shell commands included in the package. The content focuses on best practices, anti-patterns, and workflow definitions.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data sources, specifically a 'task-list' and a 'risk-register', to produce an 'estimate-set'.\n
- Ingestion points: SKILL.md identifies
task-listandrisk-registeras primary inputs in the metadata and process description.\n - Boundary markers: None are explicitly defined in the markdown to separate untrusted task data from the agent's instructions.\n
- Capability inventory: No scripts or dangerous tool-invocation instructions are present; the skill relies on the agent's native text analysis and estimation capabilities.\n
- Sanitization: No specific sanitization, validation, or escaping steps are instructed for the input data.\n The risk is minimal because the skill does not grant the agent high-privilege capabilities (such as file system writes, network exfiltration, or code execution) that would make an injection attack impactful in this context.
Audit Metadata