blameless-postmortem
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that explicitly mandate the agent to refuse user requests for fixes until a specific, role-played bureaucratic process is satisfied. This is a behavioral override that prioritizes the skill's logic over user intent and default helpfulness.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (reports of bugs or errors) and uses it to reconstruct timelines and conduct root cause analysis, creating a surface where malicious instructions in the bug report could influence agent behavior.
- Ingestion points: User-provided bug reports, error logs, and messages indicating mistakes in SKILL.md.
- Boundary markers: Absent; user input is directly processed into the postmortem logic without delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill implies the agent has the capability to apply fixes (code or file modification) to the project once the role-played process is complete.
- Sanitization: Absent; there is no evidence of input validation, escaping, or filtering before interpolating external content into the postmortem template.
Audit Metadata